System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a generated artificial intelligence to play a role of a seller; means for a user to set a role of a buyer and input a negotiation scenario; means for preparing the negotiation scenario based on input information of the user; means for simulating a negotiation between the user and the generated artificial intelligence; and means for analyzing a negotiation result and providing feedback to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, the spread of online shopping has led to a decline in opportunities to purchase goods in brick-and-mortar stores. As a result, consumers face the challenge of lacking effective negotiation strategies and communication skills in brick-and-mortar stores. This challenge is particularly pronounced in price negotiation situations, where consumers are often placed at a disadvantage. The present invention aims to solve this problem by providing a system for learning price negotiation skills using generated artificial intelligence. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. It includes a means for the generated AI to play the role of the seller, and a means for the user to set the role of the buyer and input a negotiation scenario. It also includes a means for preparing a negotiation scenario based on the information input by the user and simulating a negotiation between the user and the generated AI. It also includes a means for analyzing the negotiation results and providing feedback to the user. This allows the user to learn effective negotiation strategies and communication techniques that can be used in real life.

[0006] Specifically, the system further includes a means for the user to select a negotiation scenario on a scenario setting screen and input the product name and desired price. The system also includes a means for the generated AI to perform natural language processing on the user's utterances and generate appropriate responses. This provides a real-time negotiation experience and promotes the acquisition of effective negotiation skills.

[0007] "Generated artificial intelligence" is an interactive artificial intelligence system generated using natural language processing and machine learning algorithms.

[0008] The "role of seller" refers to the position of determining product pricing and sales conditions, and conducting transactions and negotiations with users.

[0009] A "user" is a person who seeks to gain valuable experience using the system and who plays the role of a buyer in a negotiation scenario.

[0010] The "buyer role" refers to the position in which one negotiates to purchase a product.

[0011] A "negotiation scenario" refers to a situation or story set up to simulate the progression of a conversation or transaction under specific circumstances.

[0012] "Input methods" are the interfaces and functions that users use to provide information to a system.

[0013] "Preparation means" refers to the processes and functions for constructing negotiation scenarios based on collected information and initiating simulations.

[0014] "Means to simulate" refers to the processes and functions that allow users and AI to have a back-and-forth dialogue to provide a realistic negotiation experience.

[0015] "Means of analysis and provision" refers to the processes and functions for evaluating the negotiation process and providing users with feedback such as success points and areas for improvement. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system that allows users to learn price negotiation skills by utilizing generated artificial intelligence, and specifically, is configured as follows.

[0038] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[0039] The device then sends this information to the server, which then generates a seller profile and detailed product information corresponding to the selected scenario based on the received information. Specifically, it sets the regular price of tomatoes to 100 yen each and creates a character for the seller. At this stage, the server completes preparations for the negotiation simulation.

[0040] When the user initiates negotiations, the device begins a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user with, "Hello, what are you looking for?" The user responds, "Hello, can you give me a discount on the tomatoes?" The AI ​​responds, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0041] The AI ​​analyzes the user's suggestion and returns an appropriate response (e.g., "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price."). During this process, the AI ​​uses natural language processing technology to understand what the user is saying and generate natural dialogue.

[0042] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0043] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real stores. In addition, by increasing the variety of scenarios, users can acquire skills to handle a variety of situations.

[0044] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue. Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0045] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] Terminal: The user starts the system and accesses the scenario setting screen.

[0049] Step 2:

[0050] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[0051] Step 3:

[0052] Terminal: Sends user input information to the server.

[0053] Step 4:

[0054] Server: Based on the received information, it generates background information and seller profiles for the selected scenario.

[0055] Step 5:

[0056] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[0057] Step 6:

[0058] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[0059] Step 7:

[0060] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[0061] Step 8:

[0062] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[0063] Step 9:

[0064] Terminal: The user inputs a question to the seller (artificial intelligence) such as "Hello, can I get a discount on tomatoes?"

[0065] Step 10:

[0066] Server: The generated AI analyzes the user's statements using natural language processing and generates an appropriate response.

[0067] Step 11:

[0068] Server: Generates a response and sends it to the device (e.g., "Of course. How much are you thinking?").

[0069] Step 12:

[0070] Terminal: The user enters the desired price (e.g., "Can I get four for 300 yen?").

[0071] Step 13:

[0072] Server: Artificial intelligence analyzes the desired price and generates an appropriate response (e.g., "I'm sorry, but that's a bit steep. 350 yen for four is the maximum price we can offer.").

[0073] Step 14:

[0074] Server: Sends the generated response to the device.

[0075] Step 15:

[0076] Terminal: Receives the results of the negotiation and displays them to the user.

[0077] Step 16:

[0078] Server: After the negotiation is completed, analyze the whole process of the negotiation and generate specific feedback for the user.

[0079] Step 17:

[0080] Server: Sends feedback to the device (e.g., "The opening greeting was good. Your proposed price was above the other party's limit, so next time you should adjust the negotiation flexibly while watching their reaction.").

[0081] Step 18:

[0082] Terminal: Display feedback to the user.

[0083] Through this series of processing steps, the user can learn effective negotiation skills through a price negotiation simulation using the generated artificial intelligence.

[0084] Example 1

[0085] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0086] In real-world stores and commercial environments, price negotiation is an important skill, but opportunities to effectively learn it are limited. Furthermore, conventional methods do not simulate negotiations realistically and are not sufficient for acquiring practical skills. Therefore, a system that allows users to effectively learn real-world negotiation skills is needed.

[0087] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0088] In this invention, the server includes: means for the generated AI to play the role of a seller; means for a user to set the role of a buyer and input a negotiation scenario; means for preparing a negotiation scenario based on the information input by the user; means for the generated AI to obtain detailed information about a product from a database and generate a negotiation scenario based on the information; means for simulating negotiation between a user and the generated AI; means for the AI ​​to analyze the user's comments and generate an appropriate response; and means for analyzing the negotiation results and providing feedback to the user. This allows the user to receive specific feedback through a realistic negotiation simulation and effectively learn practical negotiation skills.

[0089] A "generated artificial intelligence" is an artificial intelligence model created to play the role of a seller in a negotiation simulation with a user.

[0090] The "scenario setting screen" is an interface that allows the user to select a negotiation scenario on the displayed screen and input detailed information such as the product name and desired price.

[0091] A "database" is a data management system for storing information such as detailed product information and price data.

[0092] A "prompt sentence" is text that the generated AI uses when performing natural language processing on a user's utterance, and includes instructions and hints for generating an appropriate response.

[0093] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0094] The "negotiation scenario" indicates the specific scenario settings and conditions used in the negotiation simulation, and includes information such as the product name and desired price entered by the user.

[0095] "Feedback" refers to evaluations and points for improvement provided to the user based on the results of the negotiation simulation, and includes specific advice that the user can use in the next negotiation.

[0096] This invention relates to a system that uses generated artificial intelligence to help users learn price negotiation skills. Specifically, the system is implemented based on the following configuration and procedures.

[0097] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I'd like 300 yen for four." The scenario setting screen is provided as a user interface and accepts this information input.

[0098] The device then sends this information to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. At this stage, the server uses a generative AI model to obtain detailed product information from a database and generates a negotiation scenario based on that information. For example, the server may set the regular price of tomatoes to 100 yen each and set the seller's character. At this preparation stage, the server generates prompts for the negotiation simulation.

[0099] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. Specifically, the generated AI greets the seller by saying, "Hello, what are you looking for?" The user responds, "Hello, can I get a discount on the tomatoes?" The AI ​​then continues, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0100] During this process, the generated AI uses the prompt sentence to process natural language processing in response to the user's statement and generates an appropriate response. For example, it might respond with something like, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." During this interaction, the AI ​​uses natural language processing technology to understand the user's statement and generate a natural dialogue.

[0101] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0102] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters a desired price. The server sets the regular price of the electronics and the character of the seller, and the generated AI negotiates through dialogue. For example, if a user says, "The regular price of a refrigerator is 100,000 yen, but I'd like it to be 85,000 yen," the AI ​​playing the seller's role will respond, "That's tough, but we can do it up to 90,000 yen." Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0103] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] The user boots the system.

[0107] Specific operation: The user opens a dedicated application or web page on the device (PC, smartphone, etc.). The initial screen is displayed and the system goes into standby mode.

[0108] Input: A user action to start the system on a device.

[0109] Output: The scenario setting screen is displayed on the terminal.

[0110] Step 2:

[0111] The user selects a negotiation scenario on the scenario setting screen and enters detailed information such as the product name and desired price.

[0112] Specific operation: The user operates drop-down lists and text boxes to input information such as "negotiating a discount on tomatoes at the greengrocer" and "4 for 300 yen."

[0113] Input: Scenario selection, product name, desired price, and other details.

[0114] Output: The input information is saved on the device for later processing.

[0115] Step 3:

[0116] The terminal transmits the user's input information to the server.

[0117] Specific operation: When the user completes the information entry and clicks the submit button, the device sends the data to the server via an HTTP request.

[0118] Input: Information entered by the user, such as the scenario, product name, and desired price.

[0119] Output: The data sent to the server as an HTTP request.

[0120] Step 4:

[0121] Based on the information received, the server prepares a negotiation scenario.

[0122] Specific operation: The server retrieves the price data of the relevant product from the database and generates a prompt for the generative AI model. For example, a scenario might be set such as "The normal price of tomatoes is 100 yen, and the seller has a friendly personality."

[0123] Input: User input received via an HTTP request.

[0124] Output: Detailed information to set up the negotiation scenario (e.g. product price, seller character settings).

[0125] Step 5:

[0126] The user initiates the negotiation.

[0127] What happens: Initiate a conversation with a merchant played by a device-generated AI, for example, by saying "Hello, what are you looking for?" via voice or text.

[0128] Input: User's negotiation start operation.

[0129] Output: The dialogue with the seller AI is displayed on the screen.

[0130] Step 6:

[0131] A generative AI model analyzes what the user says and generates an appropriate response.

[0132] Specific operation: The generative AI model analyzes the user's statement, "I'd like to buy four tomatoes for 300 yen," and responds, "That's a bit tough, but how about four for 350 yen?"

[0133] Input: What the user says.

[0134] Output: An artificial intelligence response.

[0135] Step 7:

[0136] Conduct negotiations, analyze appropriate responses, and continue.

[0137] Specific operation: The generative AI model generates a similar response to the user's next utterance and continues the dialogue. For example, it might suggest, "How about four for 320 yen?", to which the model responds, "That's possible."

[0138] Input: Continuous user speech.

[0139] Output: A continuous dialogue progression.

[0140] Step 8:

[0141] The server analyzes the negotiation results and provides feedback to the user.

[0142] Specific operation: The server analyzes the negotiation log data and generates a transcript and suggestions for improvement. For example, it displays feedback on the screen such as, "The opening greeting was good. The proposed price was too high."

[0143] Input: All log data from the negotiation simulation.

[0144] Output: Display feedback to the user.

[0145] (Application example 1)

[0146] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0147] Conventional systems for learning price negotiation skills are primarily used on desktop or mobile devices and are not designed for use in real-time in-store situations. As a result, it is difficult to acquire skills that can be quickly applied in actual negotiation situations. Furthermore, feedback is provided after the negotiation is completed, which means that real-time improvement is not possible. To solve this problem, there is a need for real-time negotiation support and feedback provision in real-time in-store.

[0148] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0149] In this invention, the server includes a means for the generated AI to play the role of a seller, a means for a user to set the role of a buyer and input a negotiation scenario, a means for supporting negotiations in real time using smart glasses, a means for preparing a negotiation scenario based on information input by the user, a means for simulating negotiations between the user and the generated AI, and a means for analyzing negotiation results and providing real-time feedback to the user. This allows users to apply their price negotiation skills in real time in a physical store and instantly identify areas for improvement during negotiations and receive feedback.

[0150] "Generated AI" refers to artificial intelligence technology that uses pre-trained data and algorithms to automatically generate responses and actions to perform specific tasks.

[0151] The "seller role" refers to the role of providing goods through interactions with consumers, such as negotiations and product sales.

[0152] "User" refers to an individual who uses the system to train and improve their negotiation skills.

[0153] The "buyer role" refers to the role of negotiating or inquiring with the intention of purchasing a product.

[0154] A "negotiation scenario" is a simulation of a negotiation that takes place in a specific setting or situation, and includes predefined conditions and circumstances.

[0155] "Smart glasses" are a wearable eyeglass-type device that has augmented reality and information display functions.

[0156] "Real-time negotiation support" means that users receive feedback and assistance in real time while negotiating.

[0157] "Natural language processing" refers to the technology that enables computers to understand, generate, and process human language.

[0158] "Providing feedback" means communicating improvements and evaluations to users based on negotiation results and progress.

[0159] This invention is a system for enabling users to learn price negotiation skills by utilizing generated artificial intelligence, and is implemented as follows.

[0160] Hardware and software used

[0161] 1. Hardware

[0162] Smart glasses (e.g., wearable display devices)

[0163] Server (e.g. cloud server)

[0164] Mobile devices (e.g. smartphones)

[0165] 2. Software

[0166] Natural language processing libraries (e.g., Google Cloud Natural Language API)

[0167] Database systems (e.g. MongoDB)

[0168] Generative AI models (e.g., OpenAI GPT-4)

[0169] System configuration and operation

[0170] User-defined scenarios

[0171] When using the system, a user first operates a scenario setting screen through smart glasses or a mobile device. For example, they select a scenario such as "negotiating a discount on tomatoes at a greengrocer's" and input the product name and desired price (e.g., "4 for 300 yen").

[0172] Preparing the scenario

[0173] The terminal sends the information entered by the user to the server, which then generates a seller profile and detailed product information corresponding to the negotiation scenario based on the received information. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[0174] Negotiation initiation and simulation

[0175] When the user initiates negotiations, a dialogue with the seller, played by the generated AI, begins through an interface displayed on the smart glasses. For example, the AI ​​might say, "Hello, what are you looking for?" to which the user responds, "Hello, can you give me a discount on tomatoes?" The AI ​​then responds, "Of course. How much would you like?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can you make it 300 yen for four?").

[0176] Analysis of dialogue content and feedback

[0177] The generated AI uses natural language processing technology to understand what the user is saying and generate an appropriate response. For example, the AI ​​might respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." The user can then continue negotiating or resubmit their terms.

[0178] Once the negotiation is complete, the server analyzes the negotiation process and results and provides real-time feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0179] Examples of concrete examples and prompts

[0180] For example, the following prompt sentences can be fed into a generative AI model to generate feedback:

[0181] Example prompt sentence:

[0182] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[0183] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[0184] Based on this prompt, the generative AI model generates appropriate feedback and provides it to the user in real time, allowing the user to immediately understand areas for improvement and apply them in their next negotiation.

[0185] Through the above process, users can effectively learn practical price negotiation skills that can be used in actual negotiation situations.

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] User-defined scenarios

[0189] The user opens the scenario setting screen using smart glasses or a mobile device and inputs the negotiation scenario, product name, and desired price. For example, the user selects the scenario "Negotiating a discount on tomatoes at a greengrocer's" and inputs "tomatoes" and "4 for 300 yen." These inputs are then retrieved from the device.

[0190] Input: Scenario, product name, desired price

[0191] Output: Scenario setting information (scenario, product name, desired price)

[0192] Step 2:

[0193] Submitting and Preparing the Scenario

[0194] The terminal sends the scenario setting information entered by the user to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. Then, based on the generated information, it prepares a negotiation scenario. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[0195] Input: Scenario setting information

[0196] Output: Prepared negotiation scenario (seller profile, product details)

[0197] Step 3:

[0198] Start of negotiations

[0199] When the user starts negotiating, an interface of a seller played by the generated AI is displayed on the terminal. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds, "Hello, can I get a discount on tomatoes?" The AI ​​responds, "Of course. How much are you thinking?"

[0200] Input: Prepared negotiation scenario

[0201] Output: AI seller interface

[0202] Step 4:

[0203] Dialogue progression and analysis

[0204] The generated AI analyzes the user's statements and generates an appropriate response using natural language processing (NLP) technology. For example, if the user suggests, "Can you make it 300 yen for four?", the AI ​​will respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum." The content of the conversation is analyzed in real time and stored in a database as needed.

[0205] Input: What the user says

[0206] Output: AI response

[0207] Step 5:

[0208] Closing the negotiation and generating feedback

[0209] Once the negotiation is complete, the server analyzes the dialogue log and uses the generative AI model to generate specific feedback for the user. For example, feedback such as, "The opening greeting was good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction" may be generated. The AI ​​creates feedback based on the prompt text and notifies the user.

[0210] Input: Interaction log

[0211] Output: Feedback

[0212] Specific examples

[0213] Example prompt sentence:

[0214] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[0215] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[0216] Based on this prompt, the generative AI model generates feedback and notifies the user in real time, allowing the user to immediately understand areas for improvement and use this information for their next negotiation.

[0217] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0218] This invention relates to a system that combines generated artificial intelligence with an emotion engine to recognize a user's emotions and provide more effective dialogue responses during a negotiation simulation, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0219] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[0220] The device then sends this information to the server, which generates background information for the selected scenario and a seller profile based on the received information. At this stage, the server also initializes the emotion engine, preparing to collect user emotion data.

[0221] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?" The user responds by saying, "Hello, can I get a discount on the tomatoes?" At this stage, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[0222] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice indicates anger, the emotion engine recognizes this and sends the emotion data to the server. The server then uses this emotion data to tailor the dialogue and generate an appropriate response (e.g., "Of course, but the price is a little higher. Is that okay?").

[0223] As the negotiation progresses, the emotion engine constantly monitors the user's emotional state and detects changes. For example, if the user becomes impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. Based on this, the server generates a response to adjust or stabilize the pace of the negotiation.

[0224] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. This feedback is based on the emotional data and includes advice such as, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[0225] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real negotiation situations. At the same time, by utilizing the emotion engine, users can engage in realistic practice based on their own emotions, thereby improving their practical skills.

[0226] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[0227] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence and emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0228] The processing flow will be explained below.

[0229] Step 1:

[0230] Terminal: The user starts the system and accesses the scenario setting screen.

[0231] Step 2:

[0232] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[0233] Step 3:

[0234] Terminal: Sends user input information to the server.

[0235] Step 4:

[0236] Server: Based on the received information, it generates background information for the selected scenario and a seller profile. It also initializes the emotion engine and prepares to collect user emotion data.

[0237] Step 5:

[0238] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[0239] Step 6:

[0240] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[0241] Step 7:

[0242] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[0243] Step 8:

[0244] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[0245] Step 9:

[0246] Terminal: The user inputs a question to the seller (artificial intelligence), such as "Hello, can I get a discount on tomatoes?" At the same time, the terminal sends the user's voice and text data to the emotion engine.

[0247] Step 10:

[0248] Server: The emotion engine analyzes the user's input and recognizes their emotional state, for example detecting anger or anxiety from the user's tone of voice or text.

[0249] Step 11:

[0250] Server: The generated AI takes into account the emotional data from the emotion engine and generates an appropriate response (e.g., "Of course, but the price is a little higher. Are you sure?").

[0251] Step 12:

[0252] Server: Sends the generated response to the device.

[0253] Step 13:

[0254] Terminal: The user inputs the desired price (e.g., "Can I get 4 for 300 yen?"). This input is also sent to the emotion engine.

[0255] Step 14:

[0256] Server: The emotion engine analyzes the user's emotional state again and updates the emotion data.

[0257] Step 15:

[0258] Server: The generated AI generates an appropriate response based on the data from the emotion engine (e.g., "I'm sorry, but that's a bit harsh. 350 yen for four pieces is the maximum price.").

[0259] Step 16:

[0260] Server: Sends the generated response to the device.

[0261] Step 17:

[0262] Terminal: Receives the negotiation result and displays it to the user. At this time, the emotion engine evaluates the user's final emotional state.

[0263] Step 18:

[0264] Server: After the negotiation is completed, the entire negotiation process and emotional data are analyzed, and specific feedback is generated for the user, including emotional advice.

[0265] Step 19:

[0266] Server: Send feedback to the device (e.g., "Your first suggestion was too aggressive. Next time, please be a little more gentle with your suggestion.").

[0267] Step 20:

[0268] Terminal: Display feedback to the user.

[0269] Through this series of processing steps, users can learn effective emotion-based negotiation skills through a price negotiation simulation using the generated artificial intelligence and emotion engine.

[0270] Example 2

[0271] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0272] Conventional negotiation skill training systems involve simple interactions without considering changes in emotions, making it difficult to reproduce the complex emotional interactions that occur in actual negotiation situations. This makes it difficult for users to understand the influence of emotions in actual negotiation situations and acquire the skills to deal with them appropriately.

[0273] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0274] In this invention, the server includes a means for the generated artificial intelligence to play the role of a seller, a means for collecting emotional data from a user's voice input or text input, and a means for analyzing the user's emotional state and generating an adaptive response based on the emotional data, thereby enabling the user to learn effective emotion-based negotiation skills through a realistic negotiation simulation that takes into account changes in emotions.

[0275] "Generated artificial intelligence" refers to an artificially generated intelligence that interacts with a user and plays the role of a seller based on a specific scenario.

[0276] "User" refers to a person who uses the system to set up negotiation scenarios and enter and operate the buyer role.

[0277] A "negotiation scenario" is setting information for virtually recreating a specific negotiation situation, and refers to scenario information that is selected and input by the user within the system.

[0278] "Emotional Data" means data about a user's emotional state collected from their voice or text input.

[0279] An "emotion engine" is a software engine that analyzes the user's emotional state and adjusts the system's response and behavior based on the results.

[0280] "Adaptive response" refers to dynamic responses from the system that are generated based on the user's emotional state and the progress of the negotiation.

[0281] "Feedback" refers to specific advice and evaluation based on the user's negotiation behavior and emotional state provided after the negotiation scenario is completed.

[0282] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0283] First, when a user starts the system, a scenario setting screen appears on the device. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. This information is sent from the device to the server. Based on the received information, the server generates background information for the selected scenario and a seller profile. The server also initializes the emotion engine, preparing to collect user emotion data.

[0284] When the user initiates a negotiation, the device displays a dialogue with the seller, played by the generated AI. The AI ​​greets the seller with, "Hello, what are you looking for?", and the user responds with, "Hello, can I get a discount on tomatoes?" During this time, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[0285] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice sounds tense, the emotion engine recognizes this and sends it as emotional data to the server. The server then uses this emotional data to adjust the dialogue and generate an appropriate response, such as, "Of course, but the price is a little higher. Is that okay?"

[0286] The emotion engine constantly monitors the user's emotional state as the negotiation progresses and detects any changes. For example, if the user begins to become impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. The server receives this notification and adjusts the pace of the negotiation and the content of the response. For example, it generates a stabilizing response such as, "There are not many fresh tomatoes right now, so it's difficult to offer a discount."

[0287] Once the negotiation is complete, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. For example, the server may provide advice such as, "Your initial proposal was too aggressive. Next time, please propose in a more gentle tone." This allows the user to improve their real-life negotiation skills.

[0288] As a concrete example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[0289] An example of a prompt sentence is, "I want to buy a refrigerator at an electronics store. The desired price is under 50,000 yen. I would like to ask for your help in negotiating." By inputting this prompt sentence into the generative AI model, the system simulates a price negotiation scenario at an electronics store, the emotion engine analyzes the user's emotions, and the AI ​​provides a more realistic dialogue response. After the negotiation is completed, specific feedback is provided to the user.

[0290] This invention provides a price negotiation simulation system that uses generated artificial intelligence and an emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0292] Step 1:

[0293] The user boots the system.

[0294] Specific behavior:

[0295] 1. The user opens the application and presses a button to start the negotiation simulation.

[0296] input:

[0297] User system startup operations.

[0298] output:

[0299] The scenario setting screen will be displayed on the device.

[0300] Step 2:

[0301] The user selects a negotiation scenario on the scenario setting screen and enters detailed information.

[0302] Specific behavior:

[0303] 1. The user selects the scenario "I want to negotiate a discount on tomatoes at a greengrocer."

[0304] 2. Enter the product name "Tomatoes" and the desired price "I'd like it to be 300 yen for 4 pieces."

[0305] input:

[0306] User scenario selection and negotiation details input.

[0307] output:

[0308] The scenario entered and detailed information.

[0309] Step 3:

[0310] The terminal transmits the user's input information to the server.

[0311] Specific behavior:

[0312] 1. The device assembles the user's selected scenario and detailed information into a packet and sends it to the server.

[0313] input:

[0314] User input information (scenario and details).

[0315] output:

[0316] The data packet sent to the server.

[0317] Step 4:

[0318] Based on the information received, the server generates background information for the scenario and a profile for the seller.

[0319] Specific behavior:

[0320] 1. The server analyzes the received scenario and detailed information.

[0321] 2. Generate relevant background information based on the selected scenario.

[0322] 3. Generate the seller's character information.

[0323] input:

[0324] The scenario and details received by the server.

[0325] output:

[0326] Scenario background information and seller profile.

[0327] Step 5:

[0328] The server initializes the emotion engine and prepares it for emotion data collection.

[0329] Specific behavior:

[0330] 1. The server starts the emotion engine and performs the initialization procedure.

[0331] 2. Prepare a framework for collecting user sentiment data.

[0332] input:

[0333] Scenario information and detailed information.

[0334] output:

[0335] Initialized emotion engine and collection framework.

[0336] Step 6:

[0337] The user initiates the negotiation and the terminal displays the dialogue with the seller, played by the generated artificial intelligence.

[0338] Specific behavior:

[0339] 1. The user presses the Start Negotiation button.

[0340] 2. The terminal displays an AI-powered interactive screen for the seller.

[0341] input:

[0342] User initiated negotiation operation.

[0343] output:

[0344] The negotiation screen appears and the seller makes their first statement.

[0345] Step 7:

[0346] The device collects the user's voice and text input and sends it to the server as emotional data.

[0347] Specific behavior:

[0348] 1. The device converts the user's speech into text data using voice recognition software.

[0349] 2. The user's text input and converted voice data are converted into data packets and sent to the emotion engine.

[0350] input:

[0351] User voice and text input.

[0352] output:

[0353] Emotion data sent to the emotion engine.

[0354] Step 8:

[0355] The emotion engine analyzes the user's input to identify the emotional state and transmits the data to a server.

[0356] Specific behavior:

[0357] 1. The emotion engine analyzes the user's emotional state (e.g., tension, anger, joy) from their tone of voice, choice of words, etc.

[0358] 2. The analysis results are sent to the server as a data packet.

[0359] input:

[0360] Emotional data based on user voice and text input.

[0361] output:

[0362] Data analyzing emotional states.

[0363] Step 9:

[0364] The server adjusts the dialogue content based on the emotional data and generates adaptive responses.

[0365] Specific behavior:

[0366] 1. The server receives the emotion data and generates a response by referring to the dialogue model.

[0367] 2. The generated response is packetized and sent to the terminal.

[0368] input:

[0369] Emotional state data sent from the emotion engine.

[0370] output:

[0371] Adaptive response data.

[0372] Step 10:

[0373] The terminal displays the generated response and proceeds with the negotiation.

[0374] Specific behavior:

[0375] 1. The terminal analyzes the response data received from the server and displays it on the screen.

[0376] 2. The user makes the next statement based on the displayed response.

[0377] input:

[0378] The response data sent by the server.

[0379] output:

[0380] The response displayed on the screen and the user's next statement.

[0381] Step 11:

[0382] An emotion engine monitors the user's emotional state during the negotiation and detects changes.

[0383] Specific behavior:

[0384] 1. The emotion engine analyzes user emotion data collected in real time.

[0385] 2. Detect changes in emotions and notify the server.

[0386] input:

[0387] Emotional data collected in real time.

[0388] output:

[0389] Emotion change notification.

[0390] Step 12:

[0391] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides feedback.

[0392] Specific behavior:

[0393] 1. The server analyzes the overall data of the negotiation and evaluates the user's emotional state and behavioral patterns.

[0394] 2. Generate specific feedback messages and send them to the device.

[0395] input:

[0396] Negotiation outcomes and emotional data.

[0397] output:

[0398] Feedback message.

[0399] Through this series of processing steps, users can experience a realistic, emotionally-based negotiation simulation and improve their real-world negotiation skills.

[0400] (Application example 2)

[0401] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0402] Conventional negotiation simulation systems have difficulty providing dialogue that responds to actual emotional changes. As a result, the simulation lacks realism, making it difficult for users to fully master real negotiation skills. Furthermore, the lack of emotional response adjustment limits the learning effect.

[0403] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for collecting and analyzing emotion data from the user's voice or text input, means for adjusting the response content based on the emotion data, and means for analyzing the negotiation result and providing feedback to the user. This enables a realistic simulation according to the user's emotional state.

[0404] "Generated AI" is an artificial intelligence system that uses natural language processing techniques to simulate human interaction.

[0405] The "seller role" mimics the actions and statements of someone in a position to offer a product or service.

[0406] "A means for users to set the role of the buyer and input a negotiation scenario" refers to an interface that allows users of the system to set the role of the customer and input specific negotiation situations and conditions.

[0407] The "means for preparing a negotiation scenario" is a function for preparing the background and details of a negotiation based on information input by the user.

[0408] "Means for simulating negotiations" are techniques or methods for conducting virtual negotiations between a user and the generated AI.

[0409] "Emotion recognition means" refers to technology or devices that identify and analyze a user's emotional state from their voice or text data.

[0410] The "means for adjusting response content" is a function for optimizing the response of the artificial intelligence generated based on emotional data.

[0411] The "means for analyzing the negotiation results and providing feedback to the user" is a technique for evaluating the results of the simulation and providing the user with improvements and advice.

[0412] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0413] First, when the user starts the system, a scenario setting screen is displayed on the terminal. On this screen, the user selects a negotiation scenario and enters detailed information such as the product name and desired price. For example, the user can select "Negotiate a price at an electronics store," enter "television" as the product name, and set "desired price" to 50,000 yen. This information is sent to the server, which then prepares the scenario based on that information.

[0414] The server generates a seller profile based on the scenario information and initializes the emotion recognition means. This emotion recognition uses the existing "emotion_recognition" technology. This prepares the system to collect and analyze emotion data from the user's voice and text input in real time.

[0415] When the user starts negotiations, the generated AI plays the role of a seller and conducts a dialogue with the user. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds by saying, "Hello, can you give me a discount on the TV?" At this stage, the device analyzes the user's utterances using emotion recognition means and collects emotional data.

[0416] Emotional data is analyzed in real time to detect specific emotional states. For example, if a user's comments contain "excitement" or "anger," that emotional data is sent to the server, which then adjusts the response accordingly. Natural language processing technology is used to generate responses based on the emotional data, enabling appropriate dialogue.

[0417] During the negotiation, the device constantly monitors emotional data and detects changes in emotion. If the user begins to feel impatient or anxious, the system will slow down the pace of the negotiation or generate a comforting response. This makes the simulation more realistic, allowing the user to learn while reducing tension and stress.

[0418] Once the simulation is over, the server analyzes the negotiation results and provides specific feedback based on what it learned, such as advice like, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[0419] In this way, users can learn effective negotiation strategies and communication techniques that can be used in real-life negotiation situations. As a concrete example, if a user selects the scenario "Negotiating a discount on tomatoes at a greengrocer" and inputs "Hello, can you give me a discount on the tomatoes?" into the system, the emotion engine will recognize the emotion "excited," and the server will generate a response saying, "Of course. But the price is a little high. Is that okay?"

[0420] This allows users to acquire higher-level negotiation skills through realistic simulations that simulate actual situations.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] When a user starts the system, a scenario setting screen is displayed on the terminal. Input here is detailed information about the negotiation scenario, product name, and desired price by the user. This input data is sent by the terminal to the server. The specific operations of the terminal are to display the scenario selection screen, collect user input, and send it to the server.

[0424] Step 2:

[0425] Based on the received information, the server generates background information for the negotiation scenario and a seller profile. In addition, it initializes the emotion recognition means. The input here is the user's detailed information, and the output is a detailed scenario and the initialized emotion recognition means. Specifically, it retrieves relevant information from the database and initializes the emotion recognition engine (e.g., emotion_recognition).

[0426] Step 3:

[0427] When the user initiates a negotiation, the terminal starts a dialogue in which the generated AI plays the role of the seller. Specifically, the AI ​​presents the user with prompts such as "Hello, what are you looking for?" The input for this step is the seller's profile and background information provided by the server, and the output is an initial prompt to the user.

[0428] Step 4:

[0429] The user inputs a dialogue response (e.g., "Can I get a discount on the tomatoes?") into the terminal. The terminal sends this input data to the emotion recognition means, which analyzes the emotion data. The input here is the user's text or voice data, and the output is the analyzed emotion data. Specifically, this involves the use of voice recognition technology and text mining technology.

[0430] Step 5:

[0431] The emotion recognition means sends the analysis results to the server, which then adjusts the response content based on this emotion data. The input is the emotion recognition result, and the output is the adjusted response content (e.g., "Of course. But the price is a little higher. Is that okay?"). Specifically, the response is generated and adjusted using natural language processing technology (e.g., NLP).

[0432] Step 6:

[0433] The terminal presents the adjusted response sent from the server to the user, and the dialogue proceeds. The input here is the response data from the server, and the output is the display to the user. The specific operations are receiving data from the server and displaying it to the user.

[0434] Step 7:

[0435] As the negotiation progresses, the device constantly analyzes the user's emotional state using emotion recognition means. If the user's emotional state (e.g., impatience or anger) changes, it notifies the server. The input for this step is the user's continuous voice or text data, and the output is data on the analyzed changes in the emotional state. Specifically, this step involves performing emotion analysis in real time.

[0436] Step 8:

[0437] Once the negotiation is complete, the server analyzes the negotiation results and emotional data and provides specific feedback. The input here is all dialogue data and emotional data, and the output is feedback information (e.g., "Your first proposal was too aggressive. Next time, you should propose in a more gentle tone."). This includes analysis operations using analytical tools (e.g., data analysis software).

[0438] Step 9:

[0439] Finally, the terminal receives feedback information from the server and displays it to the user. The input here is the feedback data from the server, and the output is the display to the user. The specific operations are data reception and display operation.

[0440] This allows users to understand their own performance and learn how to improve for the next negotiation.

[0441] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0442] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0443] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0444] [Second embodiment]

[0445] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0446] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0447] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0448] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0449] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0450] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0451] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0452] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0453] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0454] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0455] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0456] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0457] The present invention relates to a system that allows users to learn price negotiation skills by utilizing generated artificial intelligence, and specifically, is configured as follows.

[0458] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[0459] The device then sends this information to the server, which then generates a seller profile and detailed product information corresponding to the selected scenario based on the received information. Specifically, it sets the regular price of tomatoes to 100 yen each and creates a character for the seller. At this stage, the server completes preparations for the negotiation simulation.

[0460] When the user initiates negotiations, the device begins a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user with, "Hello, what are you looking for?" The user responds, "Hello, can you give me a discount on the tomatoes?" The AI ​​responds, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0461] The AI ​​analyzes the user's suggestion and returns an appropriate response (e.g., "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price."). During this process, the AI ​​uses natural language processing technology to understand what the user is saying and generate natural dialogue.

[0462] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0463] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real stores. In addition, by increasing the variety of scenarios, users can acquire skills to handle a variety of situations.

[0464] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue. Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0465] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0466] The processing flow will be explained below.

[0467] Step 1:

[0468] Terminal: The user starts the system and accesses the scenario setting screen.

[0469] Step 2:

[0470] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[0471] Step 3:

[0472] Terminal: Sends user input information to the server.

[0473] Step 4:

[0474] Server: Based on the received information, it generates background information and seller profiles for the selected scenario.

[0475] Step 5:

[0476] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[0477] Step 6:

[0478] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[0479] Step 7:

[0480] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[0481] Step 8:

[0482] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[0483] Step 9:

[0484] Terminal: The user inputs a question to the seller (artificial intelligence) such as "Hello, can I get a discount on tomatoes?"

[0485] Step 10:

[0486] Server: The generated AI analyzes the user's statements using natural language processing and generates an appropriate response.

[0487] Step 11:

[0488] Server: Generates a response and sends it to the device (e.g., "Of course. How much are you thinking?").

[0489] Step 12:

[0490] Terminal: The user enters the desired price (e.g., "Can I get four for 300 yen?").

[0491] Step 13:

[0492] Server: Artificial intelligence analyzes the desired price and generates an appropriate response (e.g., "I'm sorry, but that's a bit steep. 350 yen for four is the maximum price we can offer.").

[0493] Step 14:

[0494] Server: Sends the generated response to the device.

[0495] Step 15:

[0496] Terminal: Receives the results of the negotiation and displays them to the user.

[0497] Step 16:

[0498] Server: After the negotiation is completed, analyze the whole process of the negotiation and generate specific feedback for the user.

[0499] Step 17:

[0500] Server: Sends feedback to the device (e.g., "The opening greeting was good. Your proposed price was above the other party's limit, so next time you should adjust the negotiation flexibly while watching their reaction.").

[0501] Step 18:

[0502] Terminal: Display feedback to the user.

[0503] Through this series of processing steps, the user can learn effective negotiation skills through a price negotiation simulation using the generated artificial intelligence.

[0504] Example 1

[0505] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0506] In real-world stores and commercial environments, price negotiation is an important skill, but opportunities to effectively learn it are limited. Furthermore, conventional methods do not simulate negotiations realistically and are not sufficient for acquiring practical skills. Therefore, a system that allows users to effectively learn real-world negotiation skills is needed.

[0507] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0508] In this invention, the server includes: means for the generated AI to play the role of a seller; means for a user to set the role of a buyer and input a negotiation scenario; means for preparing a negotiation scenario based on the information input by the user; means for the generated AI to obtain detailed information about a product from a database and generate a negotiation scenario based on the information; means for simulating negotiation between a user and the generated AI; means for the AI ​​to analyze the user's comments and generate an appropriate response; and means for analyzing the negotiation results and providing feedback to the user. This allows the user to receive specific feedback through a realistic negotiation simulation and effectively learn practical negotiation skills.

[0509] A "generated artificial intelligence" is an artificial intelligence model created to play the role of a seller in a negotiation simulation with a user.

[0510] The "scenario setting screen" is an interface that allows the user to select a negotiation scenario on the displayed screen and input detailed information such as the product name and desired price.

[0511] A "database" is a data management system for storing information such as detailed product information and price data.

[0512] A "prompt sentence" is text that the generated AI uses when performing natural language processing on a user's utterance, and includes instructions and hints for generating an appropriate response.

[0513] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0514] The "negotiation scenario" indicates the specific scenario settings and conditions used in the negotiation simulation, and includes information such as the product name and desired price entered by the user.

[0515] "Feedback" refers to evaluations and points for improvement provided to the user based on the results of the negotiation simulation, and includes specific advice that the user can use in the next negotiation.

[0516] This invention relates to a system that uses generated artificial intelligence to help users learn price negotiation skills. Specifically, the system is implemented based on the following configuration and procedures.

[0517] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I'd like 300 yen for four." The scenario setting screen is provided as a user interface and accepts this information input.

[0518] The device then sends this information to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. At this stage, the server uses a generative AI model to obtain detailed product information from a database and generates a negotiation scenario based on that information. For example, the server may set the regular price of tomatoes to 100 yen each and set the seller's character. At this preparation stage, the server generates prompts for the negotiation simulation.

[0519] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. Specifically, the generated AI greets the seller by saying, "Hello, what are you looking for?" The user responds, "Hello, can I get a discount on the tomatoes?" The AI ​​then continues, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0520] During this process, the generated AI uses the prompt sentence to process natural language processing in response to the user's statement and generates an appropriate response. For example, it might respond with something like, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." During this interaction, the AI ​​uses natural language processing technology to understand the user's statement and generate a natural dialogue.

[0521] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0522] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters a desired price. The server sets the regular price of the electronics and the character of the seller, and the generated AI negotiates through dialogue. For example, if a user says, "The regular price of a refrigerator is 100,000 yen, but I'd like it to be 85,000 yen," the AI ​​playing the seller's role will respond, "That's tough, but we can do it up to 90,000 yen." Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0523] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The user boots the system.

[0527] Specific operation: The user opens a dedicated application or web page on the device (PC, smartphone, etc.). The initial screen is displayed and the system goes into standby mode.

[0528] Input: A user action to start the system on a device.

[0529] Output: The scenario setting screen is displayed on the terminal.

[0530] Step 2:

[0531] The user selects a negotiation scenario on the scenario setting screen and enters detailed information such as the product name and desired price.

[0532] Specific operation: The user operates drop-down lists and text boxes to input information such as "negotiating a discount on tomatoes at the greengrocer" and "4 for 300 yen."

[0533] Input: Scenario selection, product name, desired price, and other details.

[0534] Output: The input information is saved on the device for later processing.

[0535] Step 3:

[0536] The terminal transmits the user's input information to the server.

[0537] Specific operation: When the user completes the information entry and clicks the submit button, the device sends the data to the server via an HTTP request.

[0538] Input: Information entered by the user, such as the scenario, product name, and desired price.

[0539] Output: The data sent to the server as an HTTP request.

[0540] Step 4:

[0541] Based on the information received, the server prepares a negotiation scenario.

[0542] Specific operation: The server retrieves the price data of the relevant product from the database and generates a prompt for the generative AI model. For example, a scenario might be set such as "The normal price of tomatoes is 100 yen, and the seller has a friendly personality."

[0543] Input: User input received via an HTTP request.

[0544] Output: Detailed information to set up the negotiation scenario (e.g. product price, seller character settings).

[0545] Step 5:

[0546] The user initiates the negotiation.

[0547] What happens: Initiate a conversation with a merchant played by a device-generated AI, for example, by saying "Hello, what are you looking for?" via voice or text.

[0548] Input: User's negotiation start operation.

[0549] Output: The dialogue with the seller AI is displayed on the screen.

[0550] Step 6:

[0551] A generative AI model analyzes what the user says and generates an appropriate response.

[0552] Specific operation: The generative AI model analyzes the user's statement, "I'd like to buy four tomatoes for 300 yen," and responds, "That's a bit tough, but how about four for 350 yen?"

[0553] Input: What the user says.

[0554] Output: An artificial intelligence response.

[0555] Step 7:

[0556] Conduct negotiations, analyze appropriate responses, and continue.

[0557] Specific operation: The generative AI model generates a similar response to the user's next utterance and continues the dialogue. For example, it might suggest, "How about four for 320 yen?", to which the model responds, "That's possible."

[0558] Input: Continuous user speech.

[0559] Output: A continuous dialogue progression.

[0560] Step 8:

[0561] The server analyzes the negotiation results and provides feedback to the user.

[0562] Specific operation: The server analyzes the negotiation log data and generates a transcript and suggestions for improvement. For example, it displays feedback on the screen such as, "The opening greeting was good. The proposed price was too high."

[0563] Input: All log data from the negotiation simulation.

[0564] Output: Display feedback to the user.

[0565] (Application example 1)

[0566] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Conventional systems for learning price negotiation skills are primarily used on desktop or mobile devices and are not designed for use in real-time in-store situations. As a result, it is difficult to acquire skills that can be quickly applied in actual negotiation situations. Furthermore, feedback is provided after the negotiation is completed, which means that real-time improvement is not possible. To solve this problem, there is a need for real-time negotiation support and feedback provision in real-time in-store.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0569] In this invention, the server includes a means for the generated AI to play the role of a seller, a means for a user to set the role of a buyer and input a negotiation scenario, a means for supporting negotiations in real time using smart glasses, a means for preparing a negotiation scenario based on information input by the user, a means for simulating negotiations between the user and the generated AI, and a means for analyzing negotiation results and providing real-time feedback to the user. This allows users to apply their price negotiation skills in real time in a physical store and instantly identify areas for improvement during negotiations and receive feedback.

[0570] "Generated AI" refers to artificial intelligence technology that uses pre-trained data and algorithms to automatically generate responses and actions to perform specific tasks.

[0571] The "seller role" refers to the role of providing goods through interactions with consumers, such as negotiations and product sales.

[0572] "User" refers to an individual who uses the system to train and improve their negotiation skills.

[0573] The "buyer role" refers to the role of negotiating or inquiring with the intention of purchasing a product.

[0574] A "negotiation scenario" is a simulation of a negotiation that takes place in a specific setting or situation, and includes predefined conditions and circumstances.

[0575] "Smart glasses" are a wearable eyeglass-type device that has augmented reality and information display functions.

[0576] "Real-time negotiation support" means that users receive feedback and assistance in real time while negotiating.

[0577] "Natural language processing" refers to the technology that enables computers to understand, generate, and process human language.

[0578] "Providing feedback" means communicating improvements and evaluations to users based on negotiation results and progress.

[0579] This invention is a system for enabling users to learn price negotiation skills by utilizing generated artificial intelligence, and is implemented as follows.

[0580] Hardware and software used

[0581] 1. Hardware

[0582] Smart glasses (e.g., wearable display devices)

[0583] Server (e.g. cloud server)

[0584] Mobile devices (e.g. smartphones)

[0585] 2. Software

[0586] Natural language processing libraries (e.g., Google Cloud Natural Language API)

[0587] Database systems (e.g. MongoDB)

[0588] Generative AI models (e.g., OpenAI GPT-4)

[0589] System configuration and operation

[0590] User-defined scenarios

[0591] When using the system, a user first operates a scenario setting screen through smart glasses or a mobile device. For example, they select a scenario such as "negotiating a discount on tomatoes at a greengrocer's" and input the product name and desired price (e.g., "4 for 300 yen").

[0592] Preparing the scenario

[0593] The terminal sends the information entered by the user to the server, which then generates a seller profile and detailed product information corresponding to the negotiation scenario based on the received information. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[0594] Negotiation initiation and simulation

[0595] When the user initiates negotiations, a dialogue with the seller, played by the generated AI, begins through an interface displayed on the smart glasses. For example, the AI ​​might say, "Hello, what are you looking for?" to which the user responds, "Hello, can you give me a discount on tomatoes?" The AI ​​then responds, "Of course. How much would you like?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can you make it 300 yen for four?").

[0596] Analysis of dialogue content and feedback

[0597] The generated AI uses natural language processing technology to understand what the user is saying and generate an appropriate response. For example, the AI ​​might respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." The user can then continue negotiating or resubmit their terms.

[0598] Once the negotiation is complete, the server analyzes the negotiation process and results and provides real-time feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0599] Examples of concrete examples and prompts

[0600] For example, the following prompt sentences can be fed into a generative AI model to generate feedback:

[0601] Example prompt sentence:

[0602] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[0603] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[0604] Based on this prompt, the generative AI model generates appropriate feedback and provides it to the user in real time, allowing the user to immediately understand areas for improvement and apply them in their next negotiation.

[0605] Through the above process, users can effectively learn practical price negotiation skills that can be used in actual negotiation situations.

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] User-defined scenarios

[0609] The user opens the scenario setting screen using smart glasses or a mobile device and inputs the negotiation scenario, product name, and desired price. For example, the user selects the scenario "Negotiating a discount on tomatoes at a greengrocer's" and inputs "tomatoes" and "4 for 300 yen." These inputs are then retrieved from the device.

[0610] Input: Scenario, product name, desired price

[0611] Output: Scenario setting information (scenario, product name, desired price)

[0612] Step 2:

[0613] Submitting and Preparing the Scenario

[0614] The terminal sends the scenario setting information entered by the user to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. Then, based on the generated information, it prepares a negotiation scenario. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[0615] Input: Scenario setting information

[0616] Output: Prepared negotiation scenario (seller profile, product details)

[0617] Step 3:

[0618] Start of negotiations

[0619] When the user starts negotiating, an interface of a seller played by the generated AI is displayed on the terminal. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds, "Hello, can I get a discount on tomatoes?" The AI ​​responds, "Of course. How much are you thinking?"

[0620] Input: Prepared negotiation scenario

[0621] Output: AI seller interface

[0622] Step 4:

[0623] Dialogue progression and analysis

[0624] The generated AI analyzes the user's statements and generates an appropriate response using natural language processing (NLP) technology. For example, if the user suggests, "Can you make it 300 yen for four?", the AI ​​will respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum." The content of the conversation is analyzed in real time and stored in a database as needed.

[0625] Input: What the user says

[0626] Output: AI response

[0627] Step 5:

[0628] Closing the negotiation and generating feedback

[0629] Once the negotiation is complete, the server analyzes the dialogue log and uses the generative AI model to generate specific feedback for the user. For example, feedback such as, "The opening greeting was good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction" may be generated. The AI ​​creates feedback based on the prompt text and notifies the user.

[0630] Input: Interaction log

[0631] Output: Feedback

[0632] Specific examples

[0633] Example prompt sentence:

[0634] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[0635] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[0636] Based on this prompt, the generative AI model generates feedback and notifies the user in real time, allowing the user to immediately understand areas for improvement and use this information for their next negotiation.

[0637] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0638] This invention relates to a system that combines generated artificial intelligence with an emotion engine to recognize a user's emotions and provide more effective dialogue responses during a negotiation simulation, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0639] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[0640] The device then sends this information to the server, which generates background information for the selected scenario and a seller profile based on the received information. At this stage, the server also initializes the emotion engine, preparing to collect user emotion data.

[0641] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?" The user responds by saying, "Hello, can I get a discount on the tomatoes?" At this stage, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[0642] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice indicates anger, the emotion engine recognizes this and sends the emotion data to the server. The server then uses this emotion data to tailor the dialogue and generate an appropriate response (e.g., "Of course, but the price is a little higher. Is that okay?").

[0643] As the negotiation progresses, the emotion engine constantly monitors the user's emotional state and detects changes. For example, if the user becomes impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. Based on this, the server generates a response to adjust or stabilize the pace of the negotiation.

[0644] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. This feedback is based on the emotional data and includes advice such as, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[0645] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real negotiation situations. At the same time, by utilizing the emotion engine, users can engage in realistic practice based on their own emotions, thereby improving their practical skills.

[0646] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[0647] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence and emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] Terminal: The user starts the system and accesses the scenario setting screen.

[0651] Step 2:

[0652] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[0653] Step 3:

[0654] Terminal: Sends user input information to the server.

[0655] Step 4:

[0656] Server: Based on the received information, it generates background information for the selected scenario and a seller profile. It also initializes the emotion engine and prepares to collect user emotion data.

[0657] Step 5:

[0658] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[0659] Step 6:

[0660] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[0661] Step 7:

[0662] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[0663] Step 8:

[0664] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[0665] Step 9:

[0666] Terminal: The user inputs a question to the seller (artificial intelligence), such as "Hello, can I get a discount on tomatoes?" At the same time, the terminal sends the user's voice and text data to the emotion engine.

[0667] Step 10:

[0668] Server: The emotion engine analyzes the user's input and recognizes their emotional state, for example detecting anger or anxiety from the user's tone of voice or text.

[0669] Step 11:

[0670] Server: The generated AI takes into account the emotional data from the emotion engine and generates an appropriate response (e.g., "Of course, but the price is a little higher. Are you sure?").

[0671] Step 12:

[0672] Server: Sends the generated response to the device.

[0673] Step 13:

[0674] Terminal: The user inputs the desired price (e.g., "Can I get 4 for 300 yen?"). This input is also sent to the emotion engine.

[0675] Step 14:

[0676] Server: The emotion engine analyzes the user's emotional state again and updates the emotion data.

[0677] Step 15:

[0678] Server: The generated AI generates an appropriate response based on the data from the emotion engine (e.g., "I'm sorry, but that's a bit harsh. 350 yen for four pieces is the maximum price.").

[0679] Step 16:

[0680] Server: Sends the generated response to the device.

[0681] Step 17:

[0682] Terminal: Receives the negotiation result and displays it to the user. At this time, the emotion engine evaluates the user's final emotional state.

[0683] Step 18:

[0684] Server: After the negotiation is completed, the entire negotiation process and emotional data are analyzed, and specific feedback is generated for the user, including emotional advice.

[0685] Step 19:

[0686] Server: Send feedback to the device (e.g., "Your first suggestion was too aggressive. Next time, please be a little more gentle with your suggestion.").

[0687] Step 20:

[0688] Terminal: Display feedback to the user.

[0689] Through this series of processing steps, users can learn effective emotion-based negotiation skills through a price negotiation simulation using the generated artificial intelligence and emotion engine.

[0690] Example 2

[0691] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0692] Conventional negotiation skill training systems involve simple interactions without considering changes in emotions, making it difficult to reproduce the complex emotional interactions that occur in actual negotiation situations. This makes it difficult for users to understand the influence of emotions in actual negotiation situations and acquire the skills to deal with them appropriately.

[0693] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0694] In this invention, the server includes a means for the generated artificial intelligence to play the role of a seller, a means for collecting emotional data from a user's voice input or text input, and a means for analyzing the user's emotional state and generating an adaptive response based on the emotional data, thereby enabling the user to learn effective emotion-based negotiation skills through a realistic negotiation simulation that takes into account changes in emotions.

[0695] "Generated artificial intelligence" refers to an artificially generated intelligence that interacts with a user and plays the role of a seller based on a specific scenario.

[0696] "User" refers to a person who uses the system to set up negotiation scenarios and enter and operate the buyer role.

[0697] A "negotiation scenario" is setting information for virtually recreating a specific negotiation situation, and refers to scenario information that is selected and input by the user within the system.

[0698] "Emotional Data" means data about a user's emotional state collected from their voice or text input.

[0699] An "emotion engine" is a software engine that analyzes the user's emotional state and adjusts the system's response and behavior based on the results.

[0700] "Adaptive response" refers to dynamic responses from the system that are generated based on the user's emotional state and the progress of the negotiation.

[0701] "Feedback" refers to specific advice and evaluation based on the user's negotiation behavior and emotional state provided after the negotiation scenario is completed.

[0702] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0703] First, when a user starts the system, a scenario setting screen appears on the device. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. This information is sent from the device to the server. Based on the received information, the server generates background information for the selected scenario and a seller profile. The server also initializes the emotion engine, preparing to collect user emotion data.

[0704] When the user initiates a negotiation, the device displays a dialogue with the seller, played by the generated AI. The AI ​​greets the seller with, "Hello, what are you looking for?", and the user responds with, "Hello, can I get a discount on tomatoes?" During this time, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[0705] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice sounds tense, the emotion engine recognizes this and sends it as emotional data to the server. The server then uses this emotional data to adjust the dialogue and generate an appropriate response, such as, "Of course, but the price is a little higher. Is that okay?"

[0706] The emotion engine constantly monitors the user's emotional state as the negotiation progresses and detects any changes. For example, if the user begins to become impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. The server receives this notification and adjusts the pace of the negotiation and the content of the response. For example, it generates a stabilizing response such as, "There are not many fresh tomatoes right now, so it's difficult to offer a discount."

[0707] Once the negotiation is complete, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. For example, the server may provide advice such as, "Your initial proposal was too aggressive. Next time, please propose in a more gentle tone." This allows the user to improve their real-life negotiation skills.

[0708] As a concrete example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[0709] An example of a prompt sentence is, "I want to buy a refrigerator at an electronics store. The desired price is under 50,000 yen. I would like to ask for your help in negotiating." By inputting this prompt sentence into the generative AI model, the system simulates a price negotiation scenario at an electronics store, the emotion engine analyzes the user's emotions, and the AI ​​provides a more realistic dialogue response. After the negotiation is completed, specific feedback is provided to the user.

[0710] This invention provides a price negotiation simulation system that uses generated artificial intelligence and an emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0712] Step 1:

[0713] The user boots the system.

[0714] Specific behavior:

[0715] 1. The user opens the application and presses a button to start the negotiation simulation.

[0716] input:

[0717] User system startup operations.

[0718] output:

[0719] The scenario setting screen will be displayed on the device.

[0720] Step 2:

[0721] The user selects a negotiation scenario on the scenario setting screen and enters detailed information.

[0722] Specific behavior:

[0723] 1. The user selects the scenario "I want to negotiate a discount on tomatoes at a greengrocer."

[0724] 2. Enter the product name "Tomatoes" and the desired price "I'd like it to be 300 yen for 4 pieces."

[0725] input:

[0726] User scenario selection and negotiation details input.

[0727] output:

[0728] The scenario entered and detailed information.

[0729] Step 3:

[0730] The terminal transmits the user's input information to the server.

[0731] Specific behavior:

[0732] 1. The device assembles the user's selected scenario and detailed information into a packet and sends it to the server.

[0733] input:

[0734] User input information (scenario and details).

[0735] output:

[0736] The data packet sent to the server.

[0737] Step 4:

[0738] Based on the information received, the server generates background information for the scenario and a profile for the seller.

[0739] Specific behavior:

[0740] 1. The server analyzes the received scenario and detailed information.

[0741] 2. Generate relevant background information based on the selected scenario.

[0742] 3. Generate the seller's character information.

[0743] input:

[0744] The scenario and details received by the server.

[0745] output:

[0746] Scenario background information and seller profile.

[0747] Step 5:

[0748] The server initializes the emotion engine and prepares it for emotion data collection.

[0749] Specific behavior:

[0750] 1. The server starts the emotion engine and performs the initialization procedure.

[0751] 2. Prepare a framework for collecting user sentiment data.

[0752] input:

[0753] Scenario information and detailed information.

[0754] output:

[0755] Initialized emotion engine and collection framework.

[0756] Step 6:

[0757] The user initiates the negotiation and the terminal displays the dialogue with the seller, played by the generated artificial intelligence.

[0758] Specific behavior:

[0759] 1. The user presses the Start Negotiation button.

[0760] 2. The terminal displays an AI-powered interactive screen for the seller.

[0761] input:

[0762] User initiated negotiation operation.

[0763] output:

[0764] The negotiation screen appears and the seller makes their first statement.

[0765] Step 7:

[0766] The device collects the user's voice and text input and sends it to the server as emotional data.

[0767] Specific behavior:

[0768] 1. The device converts the user's speech into text data using voice recognition software.

[0769] 2. The user's text input and converted voice data are converted into data packets and sent to the emotion engine.

[0770] input:

[0771] User voice and text input.

[0772] output:

[0773] Emotion data sent to the emotion engine.

[0774] Step 8:

[0775] The emotion engine analyzes the user's input to identify the emotional state and transmits the data to a server.

[0776] Specific behavior:

[0777] 1. The emotion engine analyzes the user's emotional state (e.g., tension, anger, joy) from their tone of voice, choice of words, etc.

[0778] 2. The analysis results are sent to the server as a data packet.

[0779] input:

[0780] Emotional data based on user voice and text input.

[0781] output:

[0782] Data analyzing emotional states.

[0783] Step 9:

[0784] The server adjusts the dialogue content based on the emotional data and generates adaptive responses.

[0785] Specific behavior:

[0786] 1. The server receives the emotion data and generates a response by referring to the dialogue model.

[0787] 2. The generated response is packetized and sent to the terminal.

[0788] input:

[0789] Emotional state data sent from the emotion engine.

[0790] output:

[0791] Adaptive response data.

[0792] Step 10:

[0793] The terminal displays the generated response and proceeds with the negotiation.

[0794] Specific behavior:

[0795] 1. The terminal analyzes the response data received from the server and displays it on the screen.

[0796] 2. The user makes the next statement based on the displayed response.

[0797] input:

[0798] The response data sent by the server.

[0799] output:

[0800] The response displayed on the screen and the user's next statement.

[0801] Step 11:

[0802] An emotion engine monitors the user's emotional state during the negotiation and detects changes.

[0803] Specific behavior:

[0804] 1. The emotion engine analyzes user emotion data collected in real time.

[0805] 2. Detect changes in emotions and notify the server.

[0806] input:

[0807] Emotional data collected in real time.

[0808] output:

[0809] Emotion change notification.

[0810] Step 12:

[0811] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides feedback.

[0812] Specific behavior:

[0813] 1. The server analyzes the overall data of the negotiation and evaluates the user's emotional state and behavioral patterns.

[0814] 2. Generate specific feedback messages and send them to the device.

[0815] input:

[0816] Negotiation outcomes and emotional data.

[0817] output:

[0818] Feedback message.

[0819] Through this series of processing steps, users can experience a realistic, emotionally-based negotiation simulation and improve their real-world negotiation skills.

[0820] (Application example 2)

[0821] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0822] Conventional negotiation simulation systems have difficulty providing dialogue that responds to actual emotional changes. As a result, the simulation lacks realism, making it difficult for users to fully master real negotiation skills. Furthermore, the lack of emotional response adjustment limits the learning effect.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for collecting and analyzing emotion data from the user's voice or text input, means for adjusting the response content based on the emotion data, and means for analyzing the negotiation result and providing feedback to the user. This enables a realistic simulation according to the user's emotional state.

[0824] "Generated AI" is an artificial intelligence system that uses natural language processing techniques to simulate human interaction.

[0825] The "seller role" mimics the actions and statements of someone in a position to offer a product or service.

[0826] "A means for users to set the role of the buyer and input a negotiation scenario" refers to an interface that allows users of the system to set the role of the customer and input specific negotiation situations and conditions.

[0827] The "means for preparing a negotiation scenario" is a function for preparing the background and details of a negotiation based on information input by the user.

[0828] "Means for simulating negotiations" are techniques or methods for conducting virtual negotiations between a user and the generated AI.

[0829] "Emotion recognition means" refers to technology or devices that identify and analyze a user's emotional state from their voice or text data.

[0830] The "means for adjusting response content" is a function for optimizing the response of the artificial intelligence generated based on emotional data.

[0831] The "means for analyzing the negotiation results and providing feedback to the user" is a technique for evaluating the results of the simulation and providing the user with improvements and advice.

[0832] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[0833] First, when the user starts the system, a scenario setting screen is displayed on the terminal. On this screen, the user selects a negotiation scenario and enters detailed information such as the product name and desired price. For example, the user can select "Negotiate a price at an electronics store," enter "television" as the product name, and set "desired price" to 50,000 yen. This information is sent to the server, which then prepares the scenario based on that information.

[0834] The server generates a seller profile based on the scenario information and initializes the emotion recognition means. This emotion recognition uses the existing "emotion_recognition" technology. This prepares the system to collect and analyze emotion data from the user's voice and text input in real time.

[0835] When the user starts negotiations, the generated AI plays the role of a seller and conducts a dialogue with the user. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds by saying, "Hello, can you give me a discount on the TV?" At this stage, the device analyzes the user's utterances using emotion recognition means and collects emotional data.

[0836] Emotional data is analyzed in real time to detect specific emotional states. For example, if a user's comments contain "excitement" or "anger," that emotional data is sent to the server, which then adjusts the response accordingly. Natural language processing technology is used to generate responses based on the emotional data, enabling appropriate dialogue.

[0837] During the negotiation, the device constantly monitors emotional data and detects changes in emotion. If the user begins to feel impatient or anxious, the system will slow down the pace of the negotiation or generate a comforting response. This makes the simulation more realistic, allowing the user to learn while reducing tension and stress.

[0838] Once the simulation is over, the server analyzes the negotiation results and provides specific feedback based on what it learned, such as advice like, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[0839] In this way, users can learn effective negotiation strategies and communication techniques that can be used in real-life negotiation situations. As a concrete example, if a user selects the scenario "Negotiating a discount on tomatoes at a greengrocer" and inputs "Hello, can you give me a discount on the tomatoes?" into the system, the emotion engine will recognize the emotion "excited," and the server will generate a response saying, "Of course. But the price is a little high. Is that okay?"

[0840] This allows users to acquire higher-level negotiation skills through realistic simulations that simulate actual situations.

[0841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0842] Step 1:

[0843] When a user starts the system, a scenario setting screen is displayed on the terminal. Input here is detailed information about the negotiation scenario, product name, and desired price by the user. This input data is sent by the terminal to the server. The specific operations of the terminal are to display the scenario selection screen, collect user input, and send it to the server.

[0844] Step 2:

[0845] Based on the received information, the server generates background information for the negotiation scenario and a seller profile. In addition, it initializes the emotion recognition means. The input here is the user's detailed information, and the output is a detailed scenario and the initialized emotion recognition means. Specifically, it retrieves relevant information from the database and initializes the emotion recognition engine (e.g., emotion_recognition).

[0846] Step 3:

[0847] When the user initiates a negotiation, the terminal starts a dialogue in which the generated AI plays the role of the seller. Specifically, the AI ​​presents the user with prompts such as "Hello, what are you looking for?" The input for this step is the seller's profile and background information provided by the server, and the output is an initial prompt to the user.

[0848] Step 4:

[0849] The user inputs a dialogue response (e.g., "Can I get a discount on the tomatoes?") into the terminal. The terminal sends this input data to the emotion recognition means, which analyzes the emotion data. The input here is the user's text or voice data, and the output is the analyzed emotion data. Specifically, this involves the use of voice recognition technology and text mining technology.

[0850] Step 5:

[0851] The emotion recognition means sends the analysis results to the server, which then adjusts the response content based on this emotion data. The input is the emotion recognition result, and the output is the adjusted response content (e.g., "Of course. But the price is a little higher. Is that okay?"). Specifically, the response is generated and adjusted using natural language processing technology (e.g., NLP).

[0852] Step 6:

[0853] The terminal presents the adjusted response sent from the server to the user, and the dialogue proceeds. The input here is the response data from the server, and the output is the display to the user. The specific operations are receiving data from the server and displaying it to the user.

[0854] Step 7:

[0855] As the negotiation progresses, the device constantly analyzes the user's emotional state using emotion recognition means. If the user's emotional state (e.g., impatience or anger) changes, it notifies the server. The input for this step is the user's continuous voice or text data, and the output is data on the analyzed changes in the emotional state. Specifically, this step involves performing emotion analysis in real time.

[0856] Step 8:

[0857] Once the negotiation is complete, the server analyzes the negotiation results and emotional data and provides specific feedback. The input here is all dialogue data and emotional data, and the output is feedback information (e.g., "Your first proposal was too aggressive. Next time, you should propose in a more gentle tone."). This includes analysis operations using analytical tools (e.g., data analysis software).

[0858] Step 9:

[0859] Finally, the terminal receives feedback information from the server and displays it to the user. The input here is the feedback data from the server, and the output is the display to the user. The specific operations are data reception and display operation.

[0860] This allows users to understand their own performance and learn how to improve for the next negotiation.

[0861] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0862] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0863] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0864] [Third embodiment]

[0865] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0866] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0867] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0868] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0869] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0870] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0871] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0872] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0873] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0874] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0875] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0876] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0877] The present invention relates to a system that allows users to learn price negotiation skills by utilizing generated artificial intelligence, and specifically, is configured as follows.

[0878] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[0879] The device then sends this information to the server, which then generates a seller profile and detailed product information corresponding to the selected scenario based on the received information. Specifically, it sets the regular price of tomatoes to 100 yen each and creates a character for the seller. At this stage, the server completes preparations for the negotiation simulation.

[0880] When the user initiates negotiations, the device begins a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user with, "Hello, what are you looking for?" The user responds, "Hello, can you give me a discount on the tomatoes?" The AI ​​responds, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0881] The AI ​​analyzes the user's suggestion and returns an appropriate response (e.g., "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price."). During this process, the AI ​​uses natural language processing technology to understand what the user is saying and generate natural dialogue.

[0882] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0883] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real stores. In addition, by increasing the variety of scenarios, users can acquire skills to handle a variety of situations.

[0884] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue. Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0885] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] Terminal: The user starts the system and accesses the scenario setting screen.

[0889] Step 2:

[0890] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[0891] Step 3:

[0892] Terminal: Sends user input information to the server.

[0893] Step 4:

[0894] Server: Based on the received information, it generates background information and seller profiles for the selected scenario.

[0895] Step 5:

[0896] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[0897] Step 6:

[0898] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[0899] Step 7:

[0900] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[0901] Step 8:

[0902] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[0903] Step 9:

[0904] Terminal: The user inputs a question to the seller (artificial intelligence) such as "Hello, can I get a discount on tomatoes?"

[0905] Step 10:

[0906] Server: The generated AI analyzes the user's statements using natural language processing and generates an appropriate response.

[0907] Step 11:

[0908] Server: Generates a response and sends it to the device (e.g., "Of course. How much are you thinking?").

[0909] Step 12:

[0910] Terminal: The user enters the desired price (e.g., "Can I get four for 300 yen?").

[0911] Step 13:

[0912] Server: Artificial intelligence analyzes the desired price and generates an appropriate response (e.g., "I'm sorry, but that's a bit steep. 350 yen for four is the maximum price we can offer.").

[0913] Step 14:

[0914] Server: Sends the generated response to the device.

[0915] Step 15:

[0916] Terminal: Receives the results of the negotiation and displays them to the user.

[0917] Step 16:

[0918] Server: After the negotiation is completed, analyze the whole process of the negotiation and generate specific feedback for the user.

[0919] Step 17:

[0920] Server: Sends feedback to the device (e.g., "The opening greeting was good. Your proposed price was above the other party's limit, so next time you should adjust the negotiation flexibly while watching their reaction.").

[0921] Step 18:

[0922] Terminal: Display feedback to the user.

[0923] Through this series of processing steps, the user can learn effective negotiation skills through a price negotiation simulation using the generated artificial intelligence.

[0924] Example 1

[0925] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0926] In real-world stores and commercial environments, price negotiation is an important skill, but opportunities to effectively learn it are limited. Furthermore, conventional methods do not simulate negotiations realistically and are not sufficient for acquiring practical skills. Therefore, a system that allows users to effectively learn real-world negotiation skills is needed.

[0927] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0928] In this invention, the server includes: means for the generated AI to play the role of a seller; means for a user to set the role of a buyer and input a negotiation scenario; means for preparing a negotiation scenario based on the information input by the user; means for the generated AI to obtain detailed information about a product from a database and generate a negotiation scenario based on the information; means for simulating negotiation between a user and the generated AI; means for the AI ​​to analyze the user's comments and generate an appropriate response; and means for analyzing the negotiation results and providing feedback to the user. This allows the user to receive specific feedback through a realistic negotiation simulation and effectively learn practical negotiation skills.

[0929] A "generated artificial intelligence" is an artificial intelligence model created to play the role of a seller in a negotiation simulation with a user.

[0930] The "scenario setting screen" is an interface that allows the user to select a negotiation scenario on the displayed screen and input detailed information such as the product name and desired price.

[0931] A "database" is a data management system for storing information such as detailed product information and price data.

[0932] A "prompt sentence" is text that the generated AI uses when performing natural language processing on a user's utterance, and includes instructions and hints for generating an appropriate response.

[0933] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[0934] The "negotiation scenario" indicates the specific scenario settings and conditions used in the negotiation simulation, and includes information such as the product name and desired price entered by the user.

[0935] "Feedback" refers to evaluations and points for improvement provided to the user based on the results of the negotiation simulation, and includes specific advice that the user can use in the next negotiation.

[0936] This invention relates to a system that uses generated artificial intelligence to help users learn price negotiation skills. Specifically, the system is implemented based on the following configuration and procedures.

[0937] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I'd like 300 yen for four." The scenario setting screen is provided as a user interface and accepts this information input.

[0938] The device then sends this information to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. At this stage, the server uses a generative AI model to obtain detailed product information from a database and generates a negotiation scenario based on that information. For example, the server may set the regular price of tomatoes to 100 yen each and set the seller's character. At this preparation stage, the server generates prompts for the negotiation simulation.

[0939] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. Specifically, the generated AI greets the seller by saying, "Hello, what are you looking for?" The user responds, "Hello, can I get a discount on the tomatoes?" The AI ​​then continues, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[0940] During this process, the generated AI uses the prompt sentence to process natural language processing in response to the user's statement and generates an appropriate response. For example, it might respond with something like, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." During this interaction, the AI ​​uses natural language processing technology to understand the user's statement and generate a natural dialogue.

[0941] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[0942] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters a desired price. The server sets the regular price of the electronics and the character of the seller, and the generated AI negotiates through dialogue. For example, if a user says, "The regular price of a refrigerator is 100,000 yen, but I'd like it to be 85,000 yen," the AI ​​playing the seller's role will respond, "That's tough, but we can do it up to 90,000 yen." Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[0943] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[0944] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0945] Step 1:

[0946] The user boots the system.

[0947] Specific operation: The user opens a dedicated application or web page on the device (PC, smartphone, etc.). The initial screen is displayed and the system goes into standby mode.

[0948] Input: A user action to start the system on a device.

[0949] Output: The scenario setting screen is displayed on the terminal.

[0950] Step 2:

[0951] The user selects a negotiation scenario on the scenario setting screen and enters detailed information such as the product name and desired price.

[0952] Specific operation: The user operates drop-down lists and text boxes to input information such as "negotiating a discount on tomatoes at the greengrocer" and "4 for 300 yen."

[0953] Input: Scenario selection, product name, desired price, and other details.

[0954] Output: The input information is saved on the device for later processing.

[0955] Step 3:

[0956] The terminal transmits the user's input information to the server.

[0957] Specific operation: When the user completes the information entry and clicks the submit button, the device sends the data to the server via an HTTP request.

[0958] Input: Information entered by the user, such as the scenario, product name, and desired price.

[0959] Output: The data sent to the server as an HTTP request.

[0960] Step 4:

[0961] Based on the information received, the server prepares a negotiation scenario.

[0962] Specific operation: The server retrieves the price data of the relevant product from the database and generates a prompt for the generative AI model. For example, a scenario might be set such as "The normal price of tomatoes is 100 yen, and the seller has a friendly personality."

[0963] Input: User input received via an HTTP request.

[0964] Output: Detailed information to set up the negotiation scenario (e.g. product price, seller character settings).

[0965] Step 5:

[0966] The user initiates the negotiation.

[0967] What happens: Initiate a conversation with a merchant played by a device-generated AI, for example, by saying "Hello, what are you looking for?" via voice or text.

[0968] Input: User's negotiation start operation.

[0969] Output: The dialogue with the seller AI is displayed on the screen.

[0970] Step 6:

[0971] A generative AI model analyzes what the user says and generates an appropriate response.

[0972] Specific operation: The generative AI model analyzes the user's statement, "I'd like to buy four tomatoes for 300 yen," and responds, "That's a bit tough, but how about four for 350 yen?"

[0973] Input: What the user says.

[0974] Output: An artificial intelligence response.

[0975] Step 7:

[0976] Conduct negotiations, analyze appropriate responses, and continue.

[0977] Specific operation: The generative AI model generates a similar response to the user's next utterance and continues the dialogue. For example, it might suggest, "How about four for 320 yen?", to which the model responds, "That's possible."

[0978] Input: Continuous user speech.

[0979] Output: A continuous dialogue progression.

[0980] Step 8:

[0981] The server analyzes the negotiation results and provides feedback to the user.

[0982] Specific operation: The server analyzes the negotiation log data and generates a transcript and suggestions for improvement. For example, it displays feedback on the screen such as, "The opening greeting was good. The proposed price was too high."

[0983] Input: All log data from the negotiation simulation.

[0984] Output: Display feedback to the user.

[0985] (Application example 1)

[0986] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0987] Conventional systems for learning price negotiation skills are primarily used on desktop or mobile devices and are not designed for use in real-time in-store situations. As a result, it is difficult to acquire skills that can be quickly applied in actual negotiation situations. Furthermore, feedback is provided after the negotiation is completed, which means that real-time improvement is not possible. To solve this problem, there is a need for real-time negotiation support and feedback provision in real-time in-store.

[0988] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0989] In this invention, the server includes a means for the generated AI to play the role of a seller, a means for a user to set the role of a buyer and input a negotiation scenario, a means for supporting negotiations in real time using smart glasses, a means for preparing a negotiation scenario based on information input by the user, a means for simulating negotiations between the user and the generated AI, and a means for analyzing negotiation results and providing real-time feedback to the user. This allows users to apply their price negotiation skills in real time in a physical store and instantly identify areas for improvement during negotiations and receive feedback.

[0990] "Generated AI" refers to artificial intelligence technology that uses pre-trained data and algorithms to automatically generate responses and actions to perform specific tasks.

[0991] The "seller role" refers to the role of providing goods through interactions with consumers, such as negotiations and product sales.

[0992] "User" refers to an individual who uses the system to train and improve their negotiation skills.

[0993] The "buyer role" refers to the role of negotiating or inquiring with the intention of purchasing a product.

[0994] A "negotiation scenario" is a simulation of a negotiation that takes place in a specific setting or situation, and includes predefined conditions and circumstances.

[0995] "Smart glasses" are a wearable eyeglass-type device that has augmented reality and information display functions.

[0996] "Real-time negotiation support" means that users receive feedback and assistance in real time while negotiating.

[0997] "Natural language processing" refers to the technology that enables computers to understand, generate, and process human language.

[0998] "Providing feedback" means communicating improvements and evaluations to users based on negotiation results and progress.

[0999] This invention is a system for enabling users to learn price negotiation skills by utilizing generated artificial intelligence, and is implemented as follows.

[1000] Hardware and software used

[1001] 1. Hardware

[1002] Smart glasses (e.g., wearable display devices)

[1003] Server (e.g. cloud server)

[1004] Mobile devices (e.g. smartphones)

[1005] 2. Software

[1006] Natural language processing libraries (e.g., Google Cloud Natural Language API)

[1007] Database systems (e.g. MongoDB)

[1008] Generative AI models (e.g., OpenAI GPT-4)

[1009] System configuration and operation

[1010] User-defined scenarios

[1011] When using the system, a user first operates a scenario setting screen through smart glasses or a mobile device. For example, they select a scenario such as "negotiating a discount on tomatoes at a greengrocer's" and input the product name and desired price (e.g., "4 for 300 yen").

[1012] Preparing the scenario

[1013] The terminal sends the information entered by the user to the server, which then generates a seller profile and detailed product information corresponding to the negotiation scenario based on the received information. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[1014] Negotiation initiation and simulation

[1015] When the user initiates negotiations, a dialogue with the seller, played by the generated AI, begins through an interface displayed on the smart glasses. For example, the AI ​​might say, "Hello, what are you looking for?" to which the user responds, "Hello, can you give me a discount on tomatoes?" The AI ​​then responds, "Of course. How much would you like?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can you make it 300 yen for four?").

[1016] Analysis of dialogue content and feedback

[1017] The generated AI uses natural language processing technology to understand what the user is saying and generate an appropriate response. For example, the AI ​​might respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." The user can then continue negotiating or resubmit their terms.

[1018] Once the negotiation is complete, the server analyzes the negotiation process and results and provides real-time feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[1019] Examples of concrete examples and prompts

[1020] For example, the following prompt sentences can be fed into a generative AI model to generate feedback:

[1021] Example prompt sentence:

[1022] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[1023] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[1024] Based on this prompt, the generative AI model generates appropriate feedback and provides it to the user in real time, allowing the user to immediately understand areas for improvement and apply them in their next negotiation.

[1025] Through the above process, users can effectively learn practical price negotiation skills that can be used in actual negotiation situations.

[1026] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1027] Step 1:

[1028] User-defined scenarios

[1029] The user opens the scenario setting screen using smart glasses or a mobile device and inputs the negotiation scenario, product name, and desired price. For example, the user selects the scenario "Negotiating a discount on tomatoes at a greengrocer's" and inputs "tomatoes" and "4 for 300 yen." These inputs are then retrieved from the device.

[1030] Input: Scenario, product name, desired price

[1031] Output: Scenario setting information (scenario, product name, desired price)

[1032] Step 2:

[1033] Submitting and Preparing the Scenario

[1034] The terminal sends the scenario setting information entered by the user to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. Then, based on the generated information, it prepares a negotiation scenario. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[1035] Input: Scenario setting information

[1036] Output: Prepared negotiation scenario (seller profile, product details)

[1037] Step 3:

[1038] Start of negotiations

[1039] When the user starts negotiating, an interface of a seller played by the generated AI is displayed on the terminal. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds, "Hello, can I get a discount on tomatoes?" The AI ​​responds, "Of course. How much are you thinking?"

[1040] Input: Prepared negotiation scenario

[1041] Output: AI seller interface

[1042] Step 4:

[1043] Dialogue progression and analysis

[1044] The generated AI analyzes the user's statements and generates an appropriate response using natural language processing (NLP) technology. For example, if the user suggests, "Can you make it 300 yen for four?", the AI ​​will respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum." The content of the conversation is analyzed in real time and stored in a database as needed.

[1045] Input: What the user says

[1046] Output: AI response

[1047] Step 5:

[1048] Closing the negotiation and generating feedback

[1049] Once the negotiation is complete, the server analyzes the dialogue log and uses the generative AI model to generate specific feedback for the user. For example, feedback such as, "The opening greeting was good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction" may be generated. The AI ​​creates feedback based on the prompt text and notifies the user.

[1050] Input: Interaction log

[1051] Output: Feedback

[1052] Specific examples

[1053] Example prompt sentence:

[1054] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[1055] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[1056] Based on this prompt, the generative AI model generates feedback and notifies the user in real time, allowing the user to immediately understand areas for improvement and use this information for their next negotiation.

[1057] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1058] This invention relates to a system that combines generated artificial intelligence with an emotion engine to recognize a user's emotions and provide more effective dialogue responses during a negotiation simulation, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1059] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[1060] The device then sends this information to the server, which generates background information for the selected scenario and a seller profile based on the received information. At this stage, the server also initializes the emotion engine, preparing to collect user emotion data.

[1061] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?" The user responds by saying, "Hello, can I get a discount on the tomatoes?" At this stage, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[1062] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice indicates anger, the emotion engine recognizes this and sends the emotion data to the server. The server then uses this emotion data to tailor the dialogue and generate an appropriate response (e.g., "Of course, but the price is a little higher. Is that okay?").

[1063] As the negotiation progresses, the emotion engine constantly monitors the user's emotional state and detects changes. For example, if the user becomes impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. Based on this, the server generates a response to adjust or stabilize the pace of the negotiation.

[1064] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. This feedback is based on the emotional data and includes advice such as, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[1065] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real negotiation situations. At the same time, by utilizing the emotion engine, users can engage in realistic practice based on their own emotions, thereby improving their practical skills.

[1066] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[1067] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence and emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1068] The processing flow will be explained below.

[1069] Step 1:

[1070] Terminal: The user starts the system and accesses the scenario setting screen.

[1071] Step 2:

[1072] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[1073] Step 3:

[1074] Terminal: Sends user input information to the server.

[1075] Step 4:

[1076] Server: Based on the received information, it generates background information for the selected scenario and a seller profile. It also initializes the emotion engine and prepares to collect user emotion data.

[1077] Step 5:

[1078] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[1079] Step 6:

[1080] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[1081] Step 7:

[1082] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[1083] Step 8:

[1084] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[1085] Step 9:

[1086] Terminal: The user inputs a question to the seller (artificial intelligence), such as "Hello, can I get a discount on tomatoes?" At the same time, the terminal sends the user's voice and text data to the emotion engine.

[1087] Step 10:

[1088] Server: The emotion engine analyzes the user's input and recognizes their emotional state, for example detecting anger or anxiety from the user's tone of voice or text.

[1089] Step 11:

[1090] Server: The generated AI takes into account the emotional data from the emotion engine and generates an appropriate response (e.g., "Of course, but the price is a little higher. Are you sure?").

[1091] Step 12:

[1092] Server: Sends the generated response to the device.

[1093] Step 13:

[1094] Terminal: The user inputs the desired price (e.g., "Can I get 4 for 300 yen?"). This input is also sent to the emotion engine.

[1095] Step 14:

[1096] Server: The emotion engine analyzes the user's emotional state again and updates the emotion data.

[1097] Step 15:

[1098] Server: The generated AI generates an appropriate response based on the data from the emotion engine (e.g., "I'm sorry, but that's a bit harsh. 350 yen for four pieces is the maximum price.").

[1099] Step 16:

[1100] Server: Sends the generated response to the device.

[1101] Step 17:

[1102] Terminal: Receives the negotiation result and displays it to the user. At this time, the emotion engine evaluates the user's final emotional state.

[1103] Step 18:

[1104] Server: After the negotiation is completed, the entire negotiation process and emotional data are analyzed, and specific feedback is generated for the user, including emotional advice.

[1105] Step 19:

[1106] Server: Send feedback to the device (e.g., "Your first suggestion was too aggressive. Next time, please be a little more gentle with your suggestion.").

[1107] Step 20:

[1108] Terminal: Display feedback to the user.

[1109] Through this series of processing steps, users can learn effective emotion-based negotiation skills through a price negotiation simulation using the generated artificial intelligence and emotion engine.

[1110] Example 2

[1111] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1112] Conventional negotiation skill training systems involve simple interactions without considering changes in emotions, making it difficult to reproduce the complex emotional interactions that occur in actual negotiation situations. This makes it difficult for users to understand the influence of emotions in actual negotiation situations and acquire the skills to deal with them appropriately.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1114] In this invention, the server includes a means for the generated artificial intelligence to play the role of a seller, a means for collecting emotional data from a user's voice input or text input, and a means for analyzing the user's emotional state and generating an adaptive response based on the emotional data, thereby enabling the user to learn effective emotion-based negotiation skills through a realistic negotiation simulation that takes into account changes in emotions.

[1115] "Generated artificial intelligence" refers to an artificially generated intelligence that interacts with a user and plays the role of a seller based on a specific scenario.

[1116] "User" refers to a person who uses the system to set up negotiation scenarios and enter and operate the buyer role.

[1117] A "negotiation scenario" is setting information for virtually recreating a specific negotiation situation, and refers to scenario information that is selected and input by the user within the system.

[1118] "Emotional Data" means data about a user's emotional state collected from their voice or text input.

[1119] An "emotion engine" is a software engine that analyzes the user's emotional state and adjusts the system's response and behavior based on the results.

[1120] "Adaptive response" refers to dynamic responses from the system that are generated based on the user's emotional state and the progress of the negotiation.

[1121] "Feedback" refers to specific advice and evaluation based on the user's negotiation behavior and emotional state provided after the negotiation scenario is completed.

[1122] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1123] First, when a user starts the system, a scenario setting screen appears on the device. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. This information is sent from the device to the server. Based on the received information, the server generates background information for the selected scenario and a seller profile. The server also initializes the emotion engine, preparing to collect user emotion data.

[1124] When the user initiates a negotiation, the device displays a dialogue with the seller, played by the generated AI. The AI ​​greets the seller with, "Hello, what are you looking for?", and the user responds with, "Hello, can I get a discount on tomatoes?" During this time, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[1125] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice sounds tense, the emotion engine recognizes this and sends it as emotional data to the server. The server then uses this emotional data to adjust the dialogue and generate an appropriate response, such as, "Of course, but the price is a little higher. Is that okay?"

[1126] The emotion engine constantly monitors the user's emotional state as the negotiation progresses and detects any changes. For example, if the user begins to become impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. The server receives this notification and adjusts the pace of the negotiation and the content of the response. For example, it generates a stabilizing response such as, "There are not many fresh tomatoes right now, so it's difficult to offer a discount."

[1127] Once the negotiation is complete, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. For example, the server may provide advice such as, "Your initial proposal was too aggressive. Next time, please propose in a more gentle tone." This allows the user to improve their real-life negotiation skills.

[1128] As a concrete example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[1129] An example of a prompt sentence is, "I want to buy a refrigerator at an electronics store. The desired price is under 50,000 yen. I would like to ask for your help in negotiating." By inputting this prompt sentence into the generative AI model, the system simulates a price negotiation scenario at an electronics store, the emotion engine analyzes the user's emotions, and the AI ​​provides a more realistic dialogue response. After the negotiation is completed, specific feedback is provided to the user.

[1130] This invention provides a price negotiation simulation system that uses generated artificial intelligence and an emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1:

[1133] The user boots the system.

[1134] Specific behavior:

[1135] 1. The user opens the application and presses a button to start the negotiation simulation.

[1136] input:

[1137] User system startup operations.

[1138] output:

[1139] The scenario setting screen will be displayed on the device.

[1140] Step 2:

[1141] The user selects a negotiation scenario on the scenario setting screen and enters detailed information.

[1142] Specific behavior:

[1143] 1. The user selects the scenario "I want to negotiate a discount on tomatoes at a greengrocer."

[1144] 2. Enter the product name "Tomatoes" and the desired price "I'd like it to be 300 yen for 4 pieces."

[1145] input:

[1146] User scenario selection and negotiation details input.

[1147] output:

[1148] The scenario entered and detailed information.

[1149] Step 3:

[1150] The terminal transmits the user's input information to the server.

[1151] Specific behavior:

[1152] 1. The device assembles the user's selected scenario and detailed information into a packet and sends it to the server.

[1153] input:

[1154] User input information (scenario and details).

[1155] output:

[1156] The data packet sent to the server.

[1157] Step 4:

[1158] Based on the information received, the server generates background information for the scenario and a profile for the seller.

[1159] Specific behavior:

[1160] 1. The server analyzes the received scenario and detailed information.

[1161] 2. Generate relevant background information based on the selected scenario.

[1162] 3. Generate the seller's character information.

[1163] input:

[1164] The scenario and details received by the server.

[1165] output:

[1166] Scenario background information and seller profile.

[1167] Step 5:

[1168] The server initializes the emotion engine and prepares it for emotion data collection.

[1169] Specific behavior:

[1170] 1. The server starts the emotion engine and performs the initialization procedure.

[1171] 2. Prepare a framework for collecting user sentiment data.

[1172] input:

[1173] Scenario information and detailed information.

[1174] output:

[1175] Initialized emotion engine and collection framework.

[1176] Step 6:

[1177] The user initiates the negotiation and the terminal displays the dialogue with the seller, played by the generated artificial intelligence.

[1178] Specific behavior:

[1179] 1. The user presses the Start Negotiation button.

[1180] 2. The terminal displays an AI-powered interactive screen for the seller.

[1181] input:

[1182] User initiated negotiation operation.

[1183] output:

[1184] The negotiation screen appears and the seller makes their first statement.

[1185] Step 7:

[1186] The device collects the user's voice and text input and sends it to the server as emotional data.

[1187] Specific behavior:

[1188] 1. The device converts the user's speech into text data using voice recognition software.

[1189] 2. The user's text input and converted voice data are converted into data packets and sent to the emotion engine.

[1190] input:

[1191] User voice and text input.

[1192] output:

[1193] Emotion data sent to the emotion engine.

[1194] Step 8:

[1195] The emotion engine analyzes the user's input to identify the emotional state and transmits the data to a server.

[1196] Specific behavior:

[1197] 1. The emotion engine analyzes the user's emotional state (e.g., tension, anger, joy) from their tone of voice, choice of words, etc.

[1198] 2. The analysis results are sent to the server as a data packet.

[1199] input:

[1200] Emotional data based on user voice and text input.

[1201] output:

[1202] Data analyzing emotional states.

[1203] Step 9:

[1204] The server adjusts the dialogue content based on the emotional data and generates adaptive responses.

[1205] Specific behavior:

[1206] 1. The server receives the emotion data and generates a response by referring to the dialogue model.

[1207] 2. The generated response is packetized and sent to the terminal.

[1208] input:

[1209] Emotional state data sent from the emotion engine.

[1210] output:

[1211] Adaptive response data.

[1212] Step 10:

[1213] The terminal displays the generated response and proceeds with the negotiation.

[1214] Specific behavior:

[1215] 1. The terminal analyzes the response data received from the server and displays it on the screen.

[1216] 2. The user makes the next statement based on the displayed response.

[1217] input:

[1218] The response data sent by the server.

[1219] output:

[1220] The response displayed on the screen and the user's next statement.

[1221] Step 11:

[1222] An emotion engine monitors the user's emotional state during the negotiation and detects changes.

[1223] Specific behavior:

[1224] 1. The emotion engine analyzes user emotion data collected in real time.

[1225] 2. Detect changes in emotions and notify the server.

[1226] input:

[1227] Emotional data collected in real time.

[1228] output:

[1229] Emotion change notification.

[1230] Step 12:

[1231] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides feedback.

[1232] Specific behavior:

[1233] 1. The server analyzes the overall data of the negotiation and evaluates the user's emotional state and behavioral patterns.

[1234] 2. Generate specific feedback messages and send them to the device.

[1235] input:

[1236] Negotiation outcomes and emotional data.

[1237] output:

[1238] Feedback message.

[1239] Through this series of processing steps, users can experience a realistic, emotionally-based negotiation simulation and improve their real-world negotiation skills.

[1240] (Application example 2)

[1241] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1242] Conventional negotiation simulation systems have difficulty providing dialogue that responds to actual emotional changes. As a result, the simulation lacks realism, making it difficult for users to fully master real negotiation skills. Furthermore, the lack of emotional response adjustment limits the learning effect.

[1243] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for collecting and analyzing emotion data from the user's voice or text input, means for adjusting the response content based on the emotion data, and means for analyzing the negotiation result and providing feedback to the user. This enables a realistic simulation according to the user's emotional state.

[1244] "Generated AI" is an artificial intelligence system that uses natural language processing techniques to simulate human interaction.

[1245] The "seller role" mimics the actions and statements of someone in a position to offer a product or service.

[1246] "A means for users to set the role of the buyer and input a negotiation scenario" refers to an interface that allows users of the system to set the role of the customer and input specific negotiation situations and conditions.

[1247] The "means for preparing a negotiation scenario" is a function for preparing the background and details of a negotiation based on information input by the user.

[1248] "Means for simulating negotiations" are techniques or methods for conducting virtual negotiations between a user and the generated AI.

[1249] "Emotion recognition means" refers to technology or devices that identify and analyze a user's emotional state from their voice or text data.

[1250] The "means for adjusting response content" is a function for optimizing the response of the artificial intelligence generated based on emotional data.

[1251] The "means for analyzing the negotiation results and providing feedback to the user" is a technique for evaluating the results of the simulation and providing the user with improvements and advice.

[1252] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1253] First, when the user starts the system, a scenario setting screen is displayed on the terminal. On this screen, the user selects a negotiation scenario and enters detailed information such as the product name and desired price. For example, the user can select "Negotiate a price at an electronics store," enter "television" as the product name, and set "desired price" to 50,000 yen. This information is sent to the server, which then prepares the scenario based on that information.

[1254] The server generates a seller profile based on the scenario information and initializes the emotion recognition means. This emotion recognition uses the existing "emotion_recognition" technology. This prepares the system to collect and analyze emotion data from the user's voice and text input in real time.

[1255] When the user starts negotiations, the generated AI plays the role of a seller and conducts a dialogue with the user. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds by saying, "Hello, can you give me a discount on the TV?" At this stage, the device analyzes the user's utterances using emotion recognition means and collects emotional data.

[1256] Emotional data is analyzed in real time to detect specific emotional states. For example, if a user's comments contain "excitement" or "anger," that emotional data is sent to the server, which then adjusts the response accordingly. Natural language processing technology is used to generate responses based on the emotional data, enabling appropriate dialogue.

[1257] During the negotiation, the device constantly monitors emotional data and detects changes in emotion. If the user begins to feel impatient or anxious, the system will slow down the pace of the negotiation or generate a comforting response. This makes the simulation more realistic, allowing the user to learn while reducing tension and stress.

[1258] Once the simulation is over, the server analyzes the negotiation results and provides specific feedback based on what it learned, such as advice like, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[1259] In this way, users can learn effective negotiation strategies and communication techniques that can be used in real-life negotiation situations. As a concrete example, if a user selects the scenario "Negotiating a discount on tomatoes at a greengrocer" and inputs "Hello, can you give me a discount on the tomatoes?" into the system, the emotion engine will recognize the emotion "excited," and the server will generate a response saying, "Of course. But the price is a little high. Is that okay?"

[1260] This allows users to acquire higher-level negotiation skills through realistic simulations that simulate actual situations.

[1261] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1262] Step 1:

[1263] When a user starts the system, a scenario setting screen is displayed on the terminal. Input here is detailed information about the negotiation scenario, product name, and desired price by the user. This input data is sent by the terminal to the server. The specific operations of the terminal are to display the scenario selection screen, collect user input, and send it to the server.

[1264] Step 2:

[1265] Based on the received information, the server generates background information for the negotiation scenario and a seller profile. In addition, it initializes the emotion recognition means. The input here is the user's detailed information, and the output is a detailed scenario and the initialized emotion recognition means. Specifically, it retrieves relevant information from the database and initializes the emotion recognition engine (e.g., emotion_recognition).

[1266] Step 3:

[1267] When the user initiates a negotiation, the terminal starts a dialogue in which the generated AI plays the role of the seller. Specifically, the AI ​​presents the user with prompts such as "Hello, what are you looking for?" The input for this step is the seller's profile and background information provided by the server, and the output is an initial prompt to the user.

[1268] Step 4:

[1269] The user inputs a dialogue response (e.g., "Can I get a discount on the tomatoes?") into the terminal. The terminal sends this input data to the emotion recognition means, which analyzes the emotion data. The input here is the user's text or voice data, and the output is the analyzed emotion data. Specifically, this involves the use of voice recognition technology and text mining technology.

[1270] Step 5:

[1271] The emotion recognition means sends the analysis results to the server, which then adjusts the response content based on this emotion data. The input is the emotion recognition result, and the output is the adjusted response content (e.g., "Of course. But the price is a little higher. Is that okay?"). Specifically, the response is generated and adjusted using natural language processing technology (e.g., NLP).

[1272] Step 6:

[1273] The terminal presents the adjusted response sent from the server to the user, and the dialogue proceeds. The input here is the response data from the server, and the output is the display to the user. The specific operations are receiving data from the server and displaying it to the user.

[1274] Step 7:

[1275] As the negotiation progresses, the device constantly analyzes the user's emotional state using emotion recognition means. If the user's emotional state (e.g., impatience or anger) changes, it notifies the server. The input for this step is the user's continuous voice or text data, and the output is data on the analyzed changes in the emotional state. Specifically, this step involves performing emotion analysis in real time.

[1276] Step 8:

[1277] Once the negotiation is complete, the server analyzes the negotiation results and emotional data and provides specific feedback. The input here is all dialogue data and emotional data, and the output is feedback information (e.g., "Your first proposal was too aggressive. Next time, you should propose in a more gentle tone."). This includes analysis operations using analytical tools (e.g., data analysis software).

[1278] Step 9:

[1279] Finally, the terminal receives feedback information from the server and displays it to the user. The input here is the feedback data from the server, and the output is the display to the user. The specific operations are data reception and display operation.

[1280] This allows users to understand their own performance and learn how to improve for the next negotiation.

[1281] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1282] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1283] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1284] [Fourth embodiment]

[1285] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1286] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1287] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1288] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1289] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1290] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1291] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1292] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1293] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1294] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1295] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1296] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1297] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1298] The present invention relates to a system that allows users to learn price negotiation skills by utilizing generated artificial intelligence, and specifically, is configured as follows.

[1299] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[1300] The device then sends this information to the server, which then generates a seller profile and detailed product information corresponding to the selected scenario based on the received information. Specifically, it sets the regular price of tomatoes to 100 yen each and creates a character for the seller. At this stage, the server completes preparations for the negotiation simulation.

[1301] When the user initiates negotiations, the device begins a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user with, "Hello, what are you looking for?" The user responds, "Hello, can you give me a discount on the tomatoes?" The AI ​​responds, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[1302] The AI ​​analyzes the user's suggestion and returns an appropriate response (e.g., "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price."). During this process, the AI ​​uses natural language processing technology to understand what the user is saying and generate natural dialogue.

[1303] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[1304] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real stores. In addition, by increasing the variety of scenarios, users can acquire skills to handle a variety of situations.

[1305] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue. Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[1306] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1307] The processing flow will be explained below.

[1308] Step 1:

[1309] Terminal: The user starts the system and accesses the scenario setting screen.

[1310] Step 2:

[1311] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[1312] Step 3:

[1313] Terminal: Sends user input information to the server.

[1314] Step 4:

[1315] Server: Based on the received information, it generates background information and seller profiles for the selected scenario.

[1316] Step 5:

[1317] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[1318] Step 6:

[1319] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[1320] Step 7:

[1321] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[1322] Step 8:

[1323] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[1324] Step 9:

[1325] Terminal: The user inputs a question to the seller (artificial intelligence) such as "Hello, can I get a discount on tomatoes?"

[1326] Step 10:

[1327] Server: The generated AI analyzes the user's statements using natural language processing and generates an appropriate response.

[1328] Step 11:

[1329] Server: Generates a response and sends it to the device (e.g., "Of course. How much are you thinking?").

[1330] Step 12:

[1331] Terminal: The user enters the desired price (e.g., "Can I get four for 300 yen?").

[1332] Step 13:

[1333] Server: Artificial intelligence analyzes the desired price and generates an appropriate response (e.g., "I'm sorry, but that's a bit steep. 350 yen for four is the maximum price we can offer.").

[1334] Step 14:

[1335] Server: Sends the generated response to the device.

[1336] Step 15:

[1337] Terminal: Receives the results of the negotiation and displays them to the user.

[1338] Step 16:

[1339] Server: After the negotiation is completed, analyze the whole process of the negotiation and generate specific feedback for the user.

[1340] Step 17:

[1341] Server: Sends feedback to the device (e.g., "The opening greeting was good. Your proposed price was above the other party's limit, so next time you should adjust the negotiation flexibly while watching their reaction.").

[1342] Step 18:

[1343] Terminal: Display feedback to the user.

[1344] Through this series of processing steps, the user can learn effective negotiation skills through a price negotiation simulation using the generated artificial intelligence.

[1345] Example 1

[1346] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1347] In real-world stores and commercial environments, price negotiation is an important skill, but opportunities to effectively learn it are limited. Furthermore, conventional methods do not simulate negotiations realistically and are not sufficient for acquiring practical skills. Therefore, a system that allows users to effectively learn real-world negotiation skills is needed.

[1348] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1349] In this invention, the server includes: means for the generated AI to play the role of a seller; means for a user to set the role of a buyer and input a negotiation scenario; means for preparing a negotiation scenario based on the information input by the user; means for the generated AI to obtain detailed information about a product from a database and generate a negotiation scenario based on the information; means for simulating negotiation between a user and the generated AI; means for the AI ​​to analyze the user's comments and generate an appropriate response; and means for analyzing the negotiation results and providing feedback to the user. This allows the user to receive specific feedback through a realistic negotiation simulation and effectively learn practical negotiation skills.

[1350] A "generated artificial intelligence" is an artificial intelligence model created to play the role of a seller in a negotiation simulation with a user.

[1351] The "scenario setting screen" is an interface that allows the user to select a negotiation scenario on the displayed screen and input detailed information such as the product name and desired price.

[1352] A "database" is a data management system for storing information such as detailed product information and price data.

[1353] A "prompt sentence" is text that the generated AI uses when performing natural language processing on a user's utterance, and includes instructions and hints for generating an appropriate response.

[1354] "Natural language processing" is a technology that allows computers to understand, analyze, and generate human language.

[1355] The "negotiation scenario" indicates the specific scenario settings and conditions used in the negotiation simulation, and includes information such as the product name and desired price entered by the user.

[1356] "Feedback" refers to evaluations and points for improvement provided to the user based on the results of the negotiation simulation, and includes specific advice that the user can use in the next negotiation.

[1357] This invention relates to a system that uses generated artificial intelligence to help users learn price negotiation skills. Specifically, the system is implemented based on the following configuration and procedures.

[1358] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I'd like 300 yen for four." The scenario setting screen is provided as a user interface and accepts this information input.

[1359] The device then sends this information to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. At this stage, the server uses a generative AI model to obtain detailed product information from a database and generates a negotiation scenario based on that information. For example, the server may set the regular price of tomatoes to 100 yen each and set the seller's character. At this preparation stage, the server generates prompts for the negotiation simulation.

[1360] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. Specifically, the generated AI greets the seller by saying, "Hello, what are you looking for?" The user responds, "Hello, can I get a discount on the tomatoes?" The AI ​​then continues, "Of course. How much are you thinking?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can I get four for 300 yen?").

[1361] During this process, the generated AI uses the prompt sentence to process natural language processing in response to the user's statement and generates an appropriate response. For example, it might respond with something like, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." During this interaction, the AI ​​uses natural language processing technology to understand the user's statement and generate a natural dialogue.

[1362] When the negotiation is over, the server analyzes the results and provides feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[1363] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters a desired price. The server sets the regular price of the electronics and the character of the seller, and the generated AI negotiates through dialogue. For example, if a user says, "The regular price of a refrigerator is 100,000 yen, but I'd like it to be 85,000 yen," the AI ​​playing the seller's role will respond, "That's tough, but we can do it up to 90,000 yen." Feedback provided after the negotiation is completed allows the user to further improve their negotiation skills.

[1364] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1365] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1366] Step 1:

[1367] The user boots the system.

[1368] Specific operation: The user opens a dedicated application or web page on the device (PC, smartphone, etc.). The initial screen is displayed and the system goes into standby mode.

[1369] Input: A user action to start the system on a device.

[1370] Output: The scenario setting screen is displayed on the terminal.

[1371] Step 2:

[1372] The user selects a negotiation scenario on the scenario setting screen and enters detailed information such as the product name and desired price.

[1373] Specific operation: The user operates drop-down lists and text boxes to input information such as "negotiating a discount on tomatoes at the greengrocer" and "4 for 300 yen."

[1374] Input: Scenario selection, product name, desired price, and other details.

[1375] Output: The input information is saved on the device for later processing.

[1376] Step 3:

[1377] The terminal transmits the user's input information to the server.

[1378] Specific operation: When the user completes the information entry and clicks the submit button, the device sends the data to the server via an HTTP request.

[1379] Input: Information entered by the user, such as the scenario, product name, and desired price.

[1380] Output: The data sent to the server as an HTTP request.

[1381] Step 4:

[1382] Based on the information received, the server prepares a negotiation scenario.

[1383] Specific operation: The server retrieves the price data of the relevant product from the database and generates a prompt for the generative AI model. For example, a scenario might be set such as "The normal price of tomatoes is 100 yen, and the seller has a friendly personality."

[1384] Input: User input received via an HTTP request.

[1385] Output: Detailed information to set up the negotiation scenario (e.g. product price, seller character settings).

[1386] Step 5:

[1387] The user initiates the negotiation.

[1388] What happens: Initiate a conversation with a merchant played by a device-generated AI, for example, by saying "Hello, what are you looking for?" via voice or text.

[1389] Input: User's negotiation start operation.

[1390] Output: The dialogue with the seller AI is displayed on the screen.

[1391] Step 6:

[1392] A generative AI model analyzes what the user says and generates an appropriate response.

[1393] Specific operation: The generative AI model analyzes the user's statement, "I'd like to buy four tomatoes for 300 yen," and responds, "That's a bit tough, but how about four for 350 yen?"

[1394] Input: What the user says.

[1395] Output: An artificial intelligence response.

[1396] Step 7:

[1397] Conduct negotiations, analyze appropriate responses, and continue.

[1398] Specific operation: The generative AI model generates a similar response to the user's next utterance and continues the dialogue. For example, it might suggest, "How about four for 320 yen?", to which the model responds, "That's possible."

[1399] Input: Continuous user speech.

[1400] Output: A continuous dialogue progression.

[1401] Step 8:

[1402] The server analyzes the negotiation results and provides feedback to the user.

[1403] Specific operation: The server analyzes the negotiation log data and generates a transcript and suggestions for improvement. For example, it displays feedback on the screen such as, "The opening greeting was good. The proposed price was too high."

[1404] Input: All log data from the negotiation simulation.

[1405] Output: Display feedback to the user.

[1406] (Application example 1)

[1407] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1408] Conventional systems for learning price negotiation skills are primarily used on desktop or mobile devices and are not designed for use in real-time in-store situations. As a result, it is difficult to acquire skills that can be quickly applied in actual negotiation situations. Furthermore, feedback is provided after the negotiation is completed, which means that real-time improvement is not possible. To solve this problem, there is a need for real-time negotiation support and feedback provision in real-time in-store.

[1409] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1410] In this invention, the server includes a means for the generated AI to play the role of a seller, a means for a user to set the role of a buyer and input a negotiation scenario, a means for supporting negotiations in real time using smart glasses, a means for preparing a negotiation scenario based on information input by the user, a means for simulating negotiations between the user and the generated AI, and a means for analyzing negotiation results and providing real-time feedback to the user. This allows users to apply their price negotiation skills in real time in a physical store and instantly identify areas for improvement during negotiations and receive feedback.

[1411] "Generated AI" refers to artificial intelligence technology that uses pre-trained data and algorithms to automatically generate responses and actions to perform specific tasks.

[1412] The "seller role" refers to the role of providing goods through interactions with consumers, such as negotiations and product sales.

[1413] "User" refers to an individual who uses the system to train and improve their negotiation skills.

[1414] The "buyer role" refers to the role of negotiating or inquiring with the intention of purchasing a product.

[1415] A "negotiation scenario" is a simulation of a negotiation that takes place in a specific setting or situation, and includes predefined conditions and circumstances.

[1416] "Smart glasses" are a wearable eyeglass-type device that has augmented reality and information display functions.

[1417] "Real-time negotiation support" means that users receive feedback and assistance in real time while negotiating.

[1418] "Natural language processing" refers to the technology that enables computers to understand, generate, and process human language.

[1419] "Providing feedback" means communicating improvements and evaluations to users based on negotiation results and progress.

[1420] This invention is a system for enabling users to learn price negotiation skills by utilizing generated artificial intelligence, and is implemented as follows.

[1421] Hardware and software used

[1422] 1. Hardware

[1423] Smart glasses (e.g., wearable display devices)

[1424] Server (e.g. cloud server)

[1425] Mobile devices (e.g. smartphones)

[1426] 2. Software

[1427] Natural language processing libraries (e.g., Google Cloud Natural Language API)

[1428] Database systems (e.g. MongoDB)

[1429] Generative AI models (e.g., OpenAI GPT-4)

[1430] System configuration and operation

[1431] User-defined scenarios

[1432] When using the system, a user first operates a scenario setting screen through smart glasses or a mobile device. For example, they select a scenario such as "negotiating a discount on tomatoes at a greengrocer's" and input the product name and desired price (e.g., "4 for 300 yen").

[1433] Preparing the scenario

[1434] The terminal sends the information entered by the user to the server, which then generates a seller profile and detailed product information corresponding to the negotiation scenario based on the received information. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[1435] Negotiation initiation and simulation

[1436] When the user initiates negotiations, a dialogue with the seller, played by the generated AI, begins through an interface displayed on the smart glasses. For example, the AI ​​might say, "Hello, what are you looking for?" to which the user responds, "Hello, can you give me a discount on tomatoes?" The AI ​​then responds, "Of course. How much would you like?" The dialogue continues in this way, with the user proposing a desired price (e.g., "Can you make it 300 yen for four?").

[1437] Analysis of dialogue content and feedback

[1438] The generated AI uses natural language processing technology to understand what the user is saying and generate an appropriate response. For example, the AI ​​might respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum price." The user can then continue negotiating or resubmit their terms.

[1439] Once the negotiation is complete, the server analyzes the negotiation process and results and provides real-time feedback to the user, including specific suggestions for improvement, such as, "Your opening greetings were good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction."

[1440] Examples of concrete examples and prompts

[1441] For example, the following prompt sentences can be fed into a generative AI model to generate feedback:

[1442] Example prompt sentence:

[1443] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[1444] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[1445] Based on this prompt, the generative AI model generates appropriate feedback and provides it to the user in real time, allowing the user to immediately understand areas for improvement and apply them in their next negotiation.

[1446] Through the above process, users can effectively learn practical price negotiation skills that can be used in actual negotiation situations.

[1447] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1448] Step 1:

[1449] User-defined scenarios

[1450] The user opens the scenario setting screen using smart glasses or a mobile device and inputs the negotiation scenario, product name, and desired price. For example, the user selects the scenario "Negotiating a discount on tomatoes at a greengrocer's" and inputs "tomatoes" and "4 for 300 yen." These inputs are then retrieved from the device.

[1451] Input: Scenario, product name, desired price

[1452] Output: Scenario setting information (scenario, product name, desired price)

[1453] Step 2:

[1454] Submitting and Preparing the Scenario

[1455] The terminal sends the scenario setting information entered by the user to the server. Based on the received information, the server generates a seller profile and detailed product information corresponding to the selected scenario. Then, based on the generated information, it prepares a negotiation scenario. For example, the regular price of tomatoes is set to 100 yen each, and a seller character is set.

[1456] Input: Scenario setting information

[1457] Output: Prepared negotiation scenario (seller profile, product details)

[1458] Step 3:

[1459] Start of negotiations

[1460] When the user starts negotiating, an interface of a seller played by the generated AI is displayed on the terminal. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds, "Hello, can I get a discount on tomatoes?" The AI ​​responds, "Of course. How much are you thinking?"

[1461] Input: Prepared negotiation scenario

[1462] Output: AI seller interface

[1463] Step 4:

[1464] Dialogue progression and analysis

[1465] The generated AI analyzes the user's statements and generates an appropriate response using natural language processing (NLP) technology. For example, if the user suggests, "Can you make it 300 yen for four?", the AI ​​will respond, "I'm sorry, but that's a bit tough. 350 yen for four is the maximum." The content of the conversation is analyzed in real time and stored in a database as needed.

[1466] Input: What the user says

[1467] Output: AI response

[1468] Step 5:

[1469] Closing the negotiation and generating feedback

[1470] Once the negotiation is complete, the server analyzes the dialogue log and uses the generative AI model to generate specific feedback for the user. For example, feedback such as, "The opening greeting was good. Your proposed price exceeded the other party's limit, so next time you should adjust your negotiations flexibly while observing their reaction" may be generated. The AI ​​creates feedback based on the prompt text and notifies the user.

[1471] Input: Interaction log

[1472] Output: Feedback

[1473] Specific examples

[1474] Example prompt sentence:

[1475] Negotiation Log: User: Can I get a discount on the tomatoes? AI: How much are you thinking?

[1476] Generate feedback like this: Your opening remarks were good. Your proposed price was above the other party's limit, so next time you should adjust your negotiations flexibly based on their reaction.

[1477] Based on this prompt, the generative AI model generates feedback and notifies the user in real time, allowing the user to immediately understand areas for improvement and use this information for their next negotiation.

[1478] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1479] This invention relates to a system that combines generated artificial intelligence with an emotion engine to recognize a user's emotions and provide more effective dialogue responses during a negotiation simulation, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1480] First, when the user starts the system, a scenario setting screen is displayed on the terminal. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. For example, the user selects "I want to negotiate a discount on tomatoes at a greengrocer's" and enters "I want 300 yen for four tomatoes."

[1481] The device then sends this information to the server, which generates background information for the selected scenario and a seller profile based on the received information. At this stage, the server also initializes the emotion engine, preparing to collect user emotion data.

[1482] When the user starts negotiating, the device starts a dialogue with the seller, played by the generated AI. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?" The user responds by saying, "Hello, can I get a discount on the tomatoes?" At this stage, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[1483] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice indicates anger, the emotion engine recognizes this and sends the emotion data to the server. The server then uses this emotion data to tailor the dialogue and generate an appropriate response (e.g., "Of course, but the price is a little higher. Is that okay?").

[1484] As the negotiation progresses, the emotion engine constantly monitors the user's emotional state and detects changes. For example, if the user becomes impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. Based on this, the server generates a response to adjust or stabilize the pace of the negotiation.

[1485] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. This feedback is based on the emotional data and includes advice such as, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[1486] Through this series of steps, users can learn effective negotiation strategies and communication techniques that can be used in real negotiation situations. At the same time, by utilizing the emotion engine, users can engage in realistic practice based on their own emotions, thereby improving their practical skills.

[1487] As a specific example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[1488] In this way, the present invention provides a price negotiation simulation system using the generated artificial intelligence and emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1489] The processing flow will be explained below.

[1490] Step 1:

[1491] Terminal: The user starts the system and accesses the scenario setting screen.

[1492] Step 2:

[1493] Terminal: The user selects a negotiation scenario and enters the product name (e.g., tomatoes) and desired price (e.g., 300 yen for 4 pieces).

[1494] Step 3:

[1495] Terminal: Sends user input information to the server.

[1496] Step 4:

[1497] Server: Based on the received information, it generates background information for the selected scenario and a seller profile. It also initializes the emotion engine and prepares to collect user emotion data.

[1498] Step 5:

[1499] Server: Set detailed product information. For example, set the regular price of tomatoes to 100 yen each and create a seller character.

[1500] Step 6:

[1501] Server: Prepares the data required for the negotiation simulation and sends it to the terminal.

[1502] Step 7:

[1503] Terminal: The user presses the "Start Negotiation" button to start the negotiation simulation.

[1504] Step 8:

[1505] Server: The generated AI starts the role of a seller and displays an initial greeting such as "Hello, what are you looking for?"

[1506] Step 9:

[1507] Terminal: The user inputs a question to the seller (artificial intelligence), such as "Hello, can I get a discount on tomatoes?" At the same time, the terminal sends the user's voice and text data to the emotion engine.

[1508] Step 10:

[1509] Server: The emotion engine analyzes the user's input and recognizes their emotional state, for example detecting anger or anxiety from the user's tone of voice or text.

[1510] Step 11:

[1511] Server: The generated AI takes into account the emotional data from the emotion engine and generates an appropriate response (e.g., "Of course, but the price is a little higher. Are you sure?").

[1512] Step 12:

[1513] Server: Sends the generated response to the device.

[1514] Step 13:

[1515] Terminal: The user inputs the desired price (e.g., "Can I get 4 for 300 yen?"). This input is also sent to the emotion engine.

[1516] Step 14:

[1517] Server: The emotion engine analyzes the user's emotional state again and updates the emotion data.

[1518] Step 15:

[1519] Server: The generated AI generates an appropriate response based on the data from the emotion engine (e.g., "I'm sorry, but that's a bit harsh. 350 yen for four pieces is the maximum price.").

[1520] Step 16:

[1521] Server: Sends the generated response to the device.

[1522] Step 17:

[1523] Terminal: Receives the negotiation result and displays it to the user. At this time, the emotion engine evaluates the user's final emotional state.

[1524] Step 18:

[1525] Server: After the negotiation is completed, the entire negotiation process and emotional data are analyzed, and specific feedback is generated for the user, including emotional advice.

[1526] Step 19:

[1527] Server: Send feedback to the device (e.g., "Your first suggestion was too aggressive. Next time, please be a little more gentle with your suggestion.").

[1528] Step 20:

[1529] Terminal: Display feedback to the user.

[1530] Through this series of processing steps, users can learn effective emotion-based negotiation skills through a price negotiation simulation using the generated artificial intelligence and emotion engine.

[1531] Example 2

[1532] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1533] Conventional negotiation skill training systems involve simple interactions without considering changes in emotions, making it difficult to reproduce the complex emotional interactions that occur in actual negotiation situations. This makes it difficult for users to understand the influence of emotions in actual negotiation situations and acquire the skills to deal with them appropriately.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1535] In this invention, the server includes a means for the generated artificial intelligence to play the role of a seller, a means for collecting emotional data from a user's voice input or text input, and a means for analyzing the user's emotional state and generating an adaptive response based on the emotional data, thereby enabling the user to learn effective emotion-based negotiation skills through a realistic negotiation simulation that takes into account changes in emotions.

[1536] "Generated artificial intelligence" refers to an artificially generated intelligence that interacts with a user and plays the role of a seller based on a specific scenario.

[1537] "User" refers to a person who uses the system to set up negotiation scenarios and enter and operate the buyer role.

[1538] A "negotiation scenario" is setting information for virtually recreating a specific negotiation situation, and refers to scenario information that is selected and input by the user within the system.

[1539] "Emotional Data" means data about a user's emotional state collected from their voice or text input.

[1540] An "emotion engine" is a software engine that analyzes the user's emotional state and adjusts the system's response and behavior based on the results.

[1541] "Adaptive response" refers to dynamic responses from the system that are generated based on the user's emotional state and the progress of the negotiation.

[1542] "Feedback" refers to specific advice and evaluation based on the user's negotiation behavior and emotional state provided after the negotiation scenario is completed.

[1543] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1544] First, when a user starts the system, a scenario setting screen appears on the device. The user selects a negotiation scenario on this screen and enters detailed information such as the product name and desired price. This information is sent from the device to the server. Based on the received information, the server generates background information for the selected scenario and a seller profile. The server also initializes the emotion engine, preparing to collect user emotion data.

[1545] When the user initiates a negotiation, the device displays a dialogue with the seller, played by the generated AI. The AI ​​greets the seller with, "Hello, what are you looking for?", and the user responds with, "Hello, can I get a discount on tomatoes?" During this time, the device collects emotion data from the user's voice and text input and sends it to the emotion engine.

[1546] The emotion engine analyzes the user's input and identifies their emotional state. For example, if the user's voice sounds tense, the emotion engine recognizes this and sends it as emotional data to the server. The server then uses this emotional data to adjust the dialogue and generate an appropriate response, such as, "Of course, but the price is a little higher. Is that okay?"

[1547] The emotion engine constantly monitors the user's emotional state as the negotiation progresses and detects any changes. For example, if the user begins to become impatient as the negotiation progresses, the emotion engine recognizes this change and notifies the server. The server receives this notification and adjusts the pace of the negotiation and the content of the response. For example, it generates a stabilizing response such as, "There are not many fresh tomatoes right now, so it's difficult to offer a discount."

[1548] Once the negotiation is complete, the server analyzes the negotiation results and the user's emotional data and provides specific feedback to the user. For example, the server may provide advice such as, "Your initial proposal was too aggressive. Next time, please propose in a more gentle tone." This allows the user to improve their real-life negotiation skills.

[1549] As a concrete example, the same procedure is applied when a user selects "Negotiating a price at an electronics store" in the scenario settings and enters the desired price. The server sets the regular price of the electronics and the seller's character, and the generated AI negotiates through dialogue while the emotion engine analyzes the user's emotional state. Feedback provided after the negotiation is completed allows the user to further improve their emotion-based negotiation skills.

[1550] An example of a prompt sentence is, "I want to buy a refrigerator at an electronics store. The desired price is under 50,000 yen. I would like to ask for your help in negotiating." By inputting this prompt sentence into the generative AI model, the system simulates a price negotiation scenario at an electronics store, the emotion engine analyzes the user's emotions, and the AI ​​provides a more realistic dialogue response. After the negotiation is completed, specific feedback is provided to the user.

[1551] This invention provides a price negotiation simulation system that uses generated artificial intelligence and an emotion engine, and provides an effective means for users to learn and improve their real-life negotiation skills.

[1552] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1553] Step 1:

[1554] The user boots the system.

[1555] Specific behavior:

[1556] 1. The user opens the application and presses a button to start the negotiation simulation.

[1557] input:

[1558] User system startup operations.

[1559] output:

[1560] The scenario setting screen will be displayed on the device.

[1561] Step 2:

[1562] The user selects a negotiation scenario on the scenario setting screen and enters detailed information.

[1563] Specific behavior:

[1564] 1. The user selects the scenario "I want to negotiate a discount on tomatoes at a greengrocer."

[1565] 2. Enter the product name "Tomatoes" and the desired price "I'd like it to be 300 yen for 4 pieces."

[1566] input:

[1567] User scenario selection and negotiation details input.

[1568] output:

[1569] The scenario entered and detailed information.

[1570] Step 3:

[1571] The terminal transmits the user's input information to the server.

[1572] Specific behavior:

[1573] 1. The device assembles the user's selected scenario and detailed information into a packet and sends it to the server.

[1574] input:

[1575] User input information (scenario and details).

[1576] output:

[1577] The data packet sent to the server.

[1578] Step 4:

[1579] Based on the information received, the server generates background information for the scenario and a profile for the seller.

[1580] Specific behavior:

[1581] 1. The server analyzes the received scenario and detailed information.

[1582] 2. Generate relevant background information based on the selected scenario.

[1583] 3. Generate the seller's character information.

[1584] input:

[1585] The scenario and details received by the server.

[1586] output:

[1587] Scenario background information and seller profile.

[1588] Step 5:

[1589] The server initializes the emotion engine and prepares it for emotion data collection.

[1590] Specific behavior:

[1591] 1. The server starts the emotion engine and performs the initialization procedure.

[1592] 2. Prepare a framework for collecting user sentiment data.

[1593] input:

[1594] Scenario information and detailed information.

[1595] output:

[1596] Initialized emotion engine and collection framework.

[1597] Step 6:

[1598] The user initiates the negotiation and the terminal displays the dialogue with the seller, played by the generated artificial intelligence.

[1599] Specific behavior:

[1600] 1. The user presses the Start Negotiation button.

[1601] 2. The terminal displays an AI-powered interactive screen for the seller.

[1602] input:

[1603] User initiated negotiation operation.

[1604] output:

[1605] The negotiation screen appears and the seller makes their first statement.

[1606] Step 7:

[1607] The device collects the user's voice and text input and sends it to the server as emotional data.

[1608] Specific behavior:

[1609] 1. The device converts the user's speech into text data using voice recognition software.

[1610] 2. The user's text input and converted voice data are converted into data packets and sent to the emotion engine.

[1611] input:

[1612] User voice and text input.

[1613] output:

[1614] Emotion data sent to the emotion engine.

[1615] Step 8:

[1616] The emotion engine analyzes the user's input to identify the emotional state and transmits the data to a server.

[1617] Specific behavior:

[1618] 1. The emotion engine analyzes the user's emotional state (e.g., tension, anger, joy) from their tone of voice, choice of words, etc.

[1619] 2. The analysis results are sent to the server as a data packet.

[1620] input:

[1621] Emotional data based on user voice and text input.

[1622] output:

[1623] Data analyzing emotional states.

[1624] Step 9:

[1625] The server adjusts the dialogue content based on the emotional data and generates adaptive responses.

[1626] Specific behavior:

[1627] 1. The server receives the emotion data and generates a response by referring to the dialogue model.

[1628] 2. The generated response is packetized and sent to the terminal.

[1629] input:

[1630] Emotional state data sent from the emotion engine.

[1631] output:

[1632] Adaptive response data.

[1633] Step 10:

[1634] The terminal displays the generated response and proceeds with the negotiation.

[1635] Specific behavior:

[1636] 1. The terminal analyzes the response data received from the server and displays it on the screen.

[1637] 2. The user makes the next statement based on the displayed response.

[1638] input:

[1639] The response data sent by the server.

[1640] output:

[1641] The response displayed on the screen and the user's next statement.

[1642] Step 11:

[1643] An emotion engine monitors the user's emotional state during the negotiation and detects changes.

[1644] Specific behavior:

[1645] 1. The emotion engine analyzes user emotion data collected in real time.

[1646] 2. Detect changes in emotions and notify the server.

[1647] input:

[1648] Emotional data collected in real time.

[1649] output:

[1650] Emotion change notification.

[1651] Step 12:

[1652] When the negotiation is completed, the server analyzes the negotiation results and the user's emotional data and provides feedback.

[1653] Specific behavior:

[1654] 1. The server analyzes the overall data of the negotiation and evaluates the user's emotional state and behavioral patterns.

[1655] 2. Generate specific feedback messages and send them to the device.

[1656] input:

[1657] Negotiation outcomes and emotional data.

[1658] output:

[1659] Feedback message.

[1660] Through this series of processing steps, users can experience a realistic, emotionally-based negotiation simulation and improve their real-world negotiation skills.

[1661] (Application example 2)

[1662] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1663] Conventional negotiation simulation systems have difficulty providing dialogue that responds to actual emotional changes. As a result, the simulation lacks realism, making it difficult for users to fully master real negotiation skills. Furthermore, the lack of emotional response adjustment limits the learning effect.

[1664] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes emotion recognition means for collecting and analyzing emotion data from the user's voice or text input, means for adjusting the response content based on the emotion data, and means for analyzing the negotiation result and providing feedback to the user. This enables a realistic simulation according to the user's emotional state.

[1665] "Generated AI" is an artificial intelligence system that uses natural language processing techniques to simulate human interaction.

[1666] The "seller role" mimics the actions and statements of someone in a position to offer a product or service.

[1667] "A means for users to set the role of the buyer and input a negotiation scenario" refers to an interface that allows users of the system to set the role of the customer and input specific negotiation situations and conditions.

[1668] The "means for preparing a negotiation scenario" is a function for preparing the background and details of a negotiation based on information input by the user.

[1669] "Means for simulating negotiations" are techniques or methods for conducting virtual negotiations between a user and the generated AI.

[1670] "Emotion recognition means" refers to technology or devices that identify and analyze a user's emotional state from their voice or text data.

[1671] The "means for adjusting response content" is a function for optimizing the response of the artificial intelligence generated based on emotional data.

[1672] The "means for analyzing the negotiation results and providing feedback to the user" is a technique for evaluating the results of the simulation and providing the user with improvements and advice.

[1673] This invention is a system that combines generated artificial intelligence with an emotion engine to recognize users' emotions and provide more effective dialogue responses during negotiation simulations, allowing users to more realistically learn real-world bargaining skills through emotion-based practice.

[1674] First, when the user starts the system, a scenario setting screen is displayed on the terminal. On this screen, the user selects a negotiation scenario and enters detailed information such as the product name and desired price. For example, the user can select "Negotiate a price at an electronics store," enter "television" as the product name, and set "desired price" to 50,000 yen. This information is sent to the server, which then prepares the scenario based on that information.

[1675] The server generates a seller profile based on the scenario information and initializes the emotion recognition means. This emotion recognition uses the existing "emotion_recognition" technology. This prepares the system to collect and analyze emotion data from the user's voice and text input in real time.

[1676] When the user starts negotiations, the generated AI plays the role of a seller and conducts a dialogue with the user. For example, the AI ​​greets the user by saying, "Hello, what are you looking for?", and the user responds by saying, "Hello, can you give me a discount on the TV?" At this stage, the device analyzes the user's utterances using emotion recognition means and collects emotional data.

[1677] Emotional data is analyzed in real time to detect specific emotional states. For example, if a user's comments contain "excitement" or "anger," that emotional data is sent to the server, which then adjusts the response accordingly. Natural language processing technology is used to generate responses based on the emotional data, enabling appropriate dialogue.

[1678] During the negotiation, the device constantly monitors emotional data and detects changes in emotion. If the user begins to feel impatient or anxious, the system will slow down the pace of the negotiation or generate a comforting response. This makes the simulation more realistic, allowing the user to learn while reducing tension and stress.

[1679] Once the simulation is over, the server analyzes the negotiation results and provides specific feedback based on what it learned, such as advice like, "Your initial proposal was too aggressive. Next time, you should propose in a more gentle tone."

[1680] In this way, users can learn effective negotiation strategies and communication techniques that can be used in real-life negotiation situations. As a concrete example, if a user selects the scenario "Negotiating a discount on tomatoes at a greengrocer" and inputs "Hello, can you give me a discount on the tomatoes?" into the system, the emotion engine will recognize the emotion "excited," and the server will generate a response saying, "Of course. But the price is a little high. Is that okay?"

[1681] This allows users to acquire higher-level negotiation skills through realistic simulations that simulate actual situations.

[1682] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1683] Step 1:

[1684] When a user starts the system, a scenario setting screen is displayed on the terminal. Input here is detailed information about the negotiation scenario, product name, and desired price by the user. This input data is sent by the terminal to the server. The specific operations of the terminal are to display the scenario selection screen, collect user input, and send it to the server.

[1685] Step 2:

[1686] Based on the received information, the server generates background information for the negotiation scenario and a seller profile. In addition, it initializes the emotion recognition means. The input here is the user's detailed information, and the output is a detailed scenario and the initialized emotion recognition means. Specifically, it retrieves relevant information from the database and initializes the emotion recognition engine (e.g., emotion_recognition).

[1687] Step 3:

[1688] When the user initiates a negotiation, the terminal starts a dialogue in which the generated AI plays the role of the seller. Specifically, the AI ​​presents the user with prompts such as "Hello, what are you looking for?" The input for this step is the seller's profile and background information provided by the server, and the output is an initial prompt to the user.

[1689] Step 4:

[1690] The user inputs a dialogue response (e.g., "Can I get a discount on the tomatoes?") into the terminal. The terminal sends this input data to the emotion recognition means, which analyzes the emotion data. The input here is the user's text or voice data, and the output is the analyzed emotion data. Specifically, this involves the use of voice recognition technology and text mining technology.

[1691] Step 5:

[1692] The emotion recognition means sends the analysis results to the server, which then adjusts the response content based on this emotion data. The input is the emotion recognition result, and the output is the adjusted response content (e.g., "Of course. But the price is a little higher. Is that okay?"). Specifically, the response is generated and adjusted using natural language processing technology (e.g., NLP).

[1693] Step 6:

[1694] The terminal presents the adjusted response sent from the server to the user, and the dialogue proceeds. The input here is the response data from the server, and the output is the display to the user. The specific operations are receiving data from the server and displaying it to the user.

[1695] Step 7:

[1696] As the negotiation progresses, the device constantly analyzes the user's emotional state using emotion recognition means. If the user's emotional state (e.g., impatience or anger) changes, it notifies the server. The input for this step is the user's continuous voice or text data, and the output is data on the analyzed changes in the emotional state. Specifically, this step involves performing emotion analysis in real time.

[1697] Step 8:

[1698] Once the negotiation is complete, the server analyzes the negotiation results and emotional data and provides specific feedback. The input here is all dialogue data and emotional data, and the output is feedback information (e.g., "Your first proposal was too aggressive. Next time, you should propose in a more gentle tone."). This includes analysis operations using analytical tools (e.g., data analysis software).

[1699] Step 9:

[1700] Finally, the terminal receives feedback information from the server and displays it to the user. The input here is the feedback data from the server, and the output is the display to the user. The specific operations are data reception and display operation.

[1701] This allows users to understand their own performance and learn how to improve for the next negotiation.

[1702] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1703] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1704] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1705] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1706] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1707] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1708] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1709] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1710] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1711] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1712] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1713] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1714] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1715] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1716] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1717] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1718] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1719] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1720] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1721] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1722] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1723] The following is further disclosed regarding the above embodiment.

[1724] (Claim 1)

[1725] A means for the generated artificial intelligence to play the role of a seller;

[1726] A means for a user to set the role of a buyer and input a negotiation scenario;

[1727] a means for preparing a negotiation scenario based on user input information;

[1728] means for simulating a negotiation between a user and the generated artificial intelligence;

[1729] a means for analyzing the negotiation results and providing feedback to the user;

[1730] A system including:

[1731] (Claim 2)

[1732] 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

[1733] (Claim 3)

[1734] 10. The system of claim 1, further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterances and generate an appropriate response.

[1735] "Example 1"

[1736] (Claim 1)

[1737] A means for the generated artificial intelligence to play the role of a seller;

[1738] A means for a user to set the role of a buyer and input a negotiation scenario;

[1739] a means for preparing a negotiation scenario based on user input information;

[1740] A means for the generated artificial intelligence to obtain detailed information about the product from a database and generate a negotiation scenario based on the information;

[1741] means for simulating a negotiation between a user and the generated artificial intelligence;

[1742] A means for artificial intelligence to analyze user comments and generate appropriate responses;

[1743] a means for analyzing the negotiation results and providing feedback to the user;

[1744] A system including:

[1745] (Claim 2)

[1746] 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

[1747] (Claim 3)

[1748] 2. The system of claim 1, further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterance using the prompt sentence to generate an appropriate response.

[1749] "Application Example 1"

[1750] (Claim 1)

[1751] A means for the generated artificial intelligence to play the role of a seller;

[1752] A means for a user to set the role of a buyer and input a negotiation scenario;

[1753] A means for supporting negotiations in real time using smart glasses;

[1754] a means for preparing a negotiation scenario based on user input information;

[1755] means for simulating a negotiation between a user and the generated artificial intelligence;

[1756] a means for analyzing the negotiation results and providing real-time feedback to the user;

[1757] A system including:

[1758] (Claim 2)

[1759] 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

[1760] (Claim 3)

[1761] 10. The system of claim 1, further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterances and generate an appropriate response.

[1762] "Example 2: Combining Emotion Engines"

[1763] (Claim 1)

[1764] A means for the generated artificial intelligence to play the role of a seller;

[1765] A means for a user to set the role of a buyer and input a negotiation scenario;

[1766] a means for preparing a negotiation scenario based on user input information;

[1767] means for simulating a negotiation between a user and the generated artificial intelligence;

[1768] a means for collecting emotion data from a user's voice input or text input;

[1769] means for analyzing the emotional state of a user and generating an adaptive response based on the emotional data;

[1770] a means for providing feedback based on negotiation results and sentiment data;

[1771] A system including:

[1772] (Claim 2)

[1773] 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

[1774] (Claim 3)

[1775] 10. The system of claim 1, further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterances and generate an appropriate response.

[1776] "Application example 2 when combining emotion engines"

[1777] (Claim 1)

[1778] A means for the generated artificial intelligence to play the role of a seller;

[1779] A means for a user to set the role of a buyer and input a negotiation scenario;

[1780] a means for preparing a negotiation scenario based on user input information;

[1781] means for simulating a negotiation between a user and the generated artificial intelligence;

[1782] An emotion recognition means for collecting and analyzing emotion data from the user's voice or text input;

[1783] means for adjusting response content based on emotion data;

[1784] a means for analyzing the negotiation results and providing feedback to the user;

[1785] A system including:

[1786] (Claim 2)

[1787] 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

[1788] (Claim 3)

[1789] 10. The system of claim 1, further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterances, tailor a response based on emotional data, and generate an appropriate reply. [Explanation of symbols]

[1790] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the generated artificial intelligence to play the role of a seller; A means for a user to set the role of a buyer and input a negotiation scenario; a means for preparing a negotiation scenario based on user input information; means for simulating a negotiation between a user and the generated artificial intelligence; a means for analyzing the negotiation results and providing feedback to the user; A system including:

2. 2. The system according to claim 1, further comprising means for allowing a user to select a negotiation scenario on a scenario setting screen and input a product name and a desired price.

3. The system according to claim 1 , further comprising means for the generated artificial intelligence to perform natural language processing on the user's utterance and generate an appropriate response.

Images