system

Abstract

We provide the system. [Solution] A system aimed at standardizing the skills of sales staff and improving productivity, A generative artificial intelligence means for generating training modules based on information from sales staff, Information processing device means for providing the generated training module to sales staff, A talk generation artificial intelligence means that generates customer service dialogue according to the information and situation of the sales staff, An information processing device that provides the generated customer interaction script to the sales staff, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Currently, there are significant variations in the skills and response quality of sales staff, which has become a factor affecting customer satisfaction. In addition, there is a lack of a system for efficiently improving the skills of individual staff, resulting in a difficult situation to improve overall productivity. Furthermore, there is also a problem that new sales staff lack appropriate support for effectively handling customer inquiries. The present invention aims to solve these problems.

Means for Solving the Problems

[0005] The present invention is a system aimed at standardizing the skills and improving the productivity of sales staff, and includes the following means: a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing device means for providing the generated training modules to sales staff; a talk generation artificial intelligence means for generating customer service talks according to the information and situation of sales staff; and an information processing device means for providing the generated customer service talks to sales staff. The generative artificial intelligence means generates training modules based on the communication skills, product knowledge, and problem-solving abilities of sales staff. The talk generation artificial intelligence means generates greetings, product descriptions, and question-answering statements according to the name of the sales staff and the customer's situation. This enables improved skills among sales staff, standardization of customer service quality, and increased productivity.

[0006] "Sales staff" are employees who provide products and services to consumers and are responsible for sales.

[0007] "Skill standardization" means maintaining a consistently high standard without variations in the abilities and quality of service of individual staff members.

[0008] "Productivity improvement" refers to efforts to achieve higher results by efficiently utilizing production resources.

[0009] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates multiple training modules based on specific information.

[0010] "Talk generation artificial intelligence means" refers to artificial intelligence technology that automatically generates dialogue content and wording based on specific situations and information.

[0011] A "training module" is a collection of training content and programs aimed at improving staff skills.

[0012] An "information processing device" is a device that consists of hardware such as servers and terminals, and software that works in conjunction with them, and processes and provides information.

[0013] "Customer service talk" refers to appropriate conversational content and statements used by sales staff when interacting with customers.

[0014] "Communication skills" refer to the ability to effectively transmit and receive information.

[0015] "Product knowledge" refers to having detailed information about the products or services being handled.

[0016] "Problem-solving ability" is the ability to analyze a problem, find a solution, and implement it. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9]It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be described.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system aimed at standardizing the skills of sales staff and improving productivity. This system is implemented as follows.

[0039] Skill content creation and delivery

[0040] 1. User requests for skill content

[0041] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0042] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0043] 2. Server receiving and processing requests

[0044] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0045] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0046] 3. Provision of generated skill content

[0047] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[0048] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0049] Generating and providing customer service dialogues

[0050] 1. Customer talk requests from users

[0051] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0052] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0053] 2. Server receiving and processing requests

[0054] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0055] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[0056] 3. Provision of generated customer interaction scripts.

[0057] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[0058] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0059] Specific example

[0060] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and generates a training module based on A's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to A via the terminal.

[0061] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI to generate specific greetings and product descriptions. The generated talks are then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[0062] As a result, the present invention can improve the skills of sales staff and standardize the quality of customer service, thereby significantly improving sales efficiency.

[0063] The following describes the processing flow.

[0064] Skill content creation and delivery

[0065] Step 1:

[0066] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0067] Step 2:

[0068] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0069] Step 3:

[0070] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0071] Step 4:

[0072] The server invokes a generative artificial intelligence (AI) system based on staff information. The AI ​​system analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0073] Step 5:

[0074] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[0075] Step 6:

[0076] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0077] Generating and providing customer service dialogues

[0078] Step 1:

[0079] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0080] Step 2:

[0081] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0082] Step 3:

[0083] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0084] Step 4:

[0085] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The talk generation AI mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[0086] Step 5:

[0087] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0088] Step 6:

[0089] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0090] (Example 1)

[0091] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Standardizing the skills and improving the productivity of sales staff are important challenges for many companies. In particular, since sales staff skills depend on individual experience and knowledge, standardizing them is difficult. Furthermore, providing high-quality customer service tailored to each situation is also not easy. Therefore, there has been a need for efficient and effective means to standardize the skills of sales staff and improve productivity.

[0093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0094] In this invention, the server includes terminal means for receiving requests from users, converting information into JSON format and sending it to the server; generative artificial intelligence means for analyzing the JSON data sent to the server, calling a generation AI model based on the analysis results and generating an appropriate training module; means for sending and displaying the generated training module again as a JSON response to the terminal; means for receiving customer service talk requests from users, analyzing data including situation and staff information, calling a talk generation artificial intelligence based on the analysis results; and means for sending and displaying the customer service talk generated by the talk generation artificial intelligence as a JSON response to the terminal. This enables the standardization of sales staff skills and high-quality customer service tailored to the situation.

[0095] A "terminal device" is a device that has the function of receiving requests from users, converting the information into JSON format, and sending it to the server.

[0096] A "generative artificial intelligence means" is a system that includes artificial intelligence that analyzes JSON data sent to a server and generates appropriate training modules based on the analysis results.

[0097] A "generative AI model" is a general term for artificial intelligence algorithms that generate training modules and customer service dialogues based on the skills and abilities of sales staff.

[0098] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a standard for organizing data into a data structure that is easy for both humans and machines to read.

[0099] A "talk generation artificial intelligence means" is a system that includes artificial intelligence that analyzes user request data and generates appropriate customer response talk based on the situation and staff information.

[0100] A "prompt sentence" is an input sentence given to a generative AI model to enable it to perform predictions or generation.

[0101] "Response" is a term that refers to the response data sent from a server to a terminal.

[0102] A "training module" is a collection of learning programs and materials designed to improve the skills of sales staff.

[0103] "Customer service dialogue" refers to phrases and explanations used for customer service in specific situations.

[0104] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system utilizes generative artificial intelligence means and talk generation artificial intelligence means to improve the skills of sales staff and the quality of customer service.

[0105] Skill content creation and delivery

[0106] First, users request training modules through the system's UI (user interface) to improve their skills. When a user enters the necessary information (ID, name, etc.) into the request form and clicks the submit button, the device converts this input data into JSON format and sends it to the server.

[0107] The server receives POST requests at a specific endpoint and parses the received data in JSON format. Next, it extracts user information (ID, name, etc.) from the parsed data and sends a prompt message to a generative artificial intelligence (e.g., GPT-4(registered trademark) API) based on this information. The generative AI generates a training module and returns a response to the server.

[0108] The server compiles the generated training modules into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then view the displayed training modules and work to improve their skills.

[0109] Generating and providing customer service dialogues

[0110] Next, the user makes a request via the UI to retrieve a conversation appropriate for a specific customer interaction situation. The user enters the situation (e.g., new customer interaction, product explanation) and their own information, and clicks the submit button, at which point the device sends this data to the server in JSON format.

[0111] The server receives POST requests at a specific endpoint and parses the data in JSON format. It extracts situation and staff information from the parsed data and uses this to send prompt messages to a talk generation artificial intelligence (e.g., GPT-4 API). The talk generation artificial intelligence generates appropriate customer service dialogue and returns a response to the server.

[0112] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then interact with the customer based on the displayed conversation.

[0113] Specific example

[0114] For example, consider the process by which a new sales staff member obtains their training module. This sales staff member logs into the system, enters their ID and name into the request form, and then clicks the submit button. The terminal converts this information into JSON format and sends it to the server. The server receives and analyzes this data, then calls a generative artificial intelligence (GPT-4) to generate a training module. The generated module is sent to the terminal as a JSON response and displayed.

[0115] Furthermore, when a new sales staff member interacts with a new customer in the store, they can request appropriate customer service dialogue. Once the staff member inputs the situation and submits the request, the terminal converts the data into JSON format and sends it to the server. The server receives and analyzes the data, invokes the dialogue generation artificial intelligence (GPT-4), and generates appropriate dialogue. The generated dialogue is then sent to the terminal as a JSON response and displayed.

[0116] Example of a prompt

[0117] An example of a prompt message in a skill content request is as follows:

[0118] "Generate training modules to improve product knowledge and problem-solving skills based on user IDs and names."

[0119] An example of a prompt in a customer talk request is as follows:

[0120] "Please generate a greeting message for new customers based on their user ID and name."

[0121] The above describes specific embodiments for carrying out the present invention. This system effectively enables the standardization of sales staff skills and improvement of productivity.

[0122] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0123] Skill content creation and delivery

[0124] Step 1:

[0125] The user makes a request

[0126] The user logs into the application to obtain the training module and enters the required information (ID, name, etc.) into the request form. The user then clicks the submit button on the form.

[0127] Input: User ID, name, and other information

[0128] Output: Event when the submit button was clicked

[0129] Step 2:

[0130] The device sends the request to the server.

[0131] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[0132] Input: User ID, name, and other information

[0133] Output: JSON data, HTTP POST request

[0134] Step 3:

[0135] The server receives the request.

[0136] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[0137] Input: JSON data, HTTP POST request

[0138] Output: Parsed user ID, name, and other information

[0139] Step 4:

[0140] The server invokes a generative artificial intelligence.

[0141] The server sends a prompt message to a generative artificial intelligence (e.g., GPT-4) based on the extracted user information. The generative AI then generates an appropriate training module based on the information received.

[0142] Input: User ID, name, and other information

[0143] Output: The generated training module (e.g., a training module on product knowledge)

[0144] Step 5:

[0145] The server sends a response to the terminal.

[0146] The server compiles the generated training modules into a JSON response and sends it back to the terminal as an HTTP response.

[0147] Input: Generated training module (in JSON format)

[0148] Output: HTTP response, data in JSON format

[0149] Step 6:

[0150] The device displays skill content.

[0151] The terminal receives a response from the server and parses its contents. It then displays the parsed training module in the user interface (UI).

[0152] Users can view the displayed skill content and begin training.

[0153] Input: JSON data, HTTP response

[0154] Output: Training modules displayed in the user interface

[0155] Generating and providing customer service dialogues.

[0156] Step 1:

[0157] The user makes a request

[0158] The user fills out a request form in the application to obtain a conversation appropriate for a specific situation. For example, they enter the situation (e.g., new customer support, product explanation) and their own information. The user then clicks the submit button on the form.

[0159] Input: Situation, User information

[0160] Output: Event when the submit button was clicked

[0161] Step 2:

[0162] The device sends the request to the server.

[0163] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[0164] Input: Situation, User information

[0165] Output: JSON data, HTTP POST request

[0166] Step 3:

[0167] The server receives the request.

[0168] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[0169] Input: JSON data, HTTP POST request

[0170] Output: Parsed situation, user information

[0171] Step 4:

[0172] The server invokes the AI ​​for generating speech.

[0173] The server sends a prompt message to the AI ​​that generates the conversation (e.g., GPT-4) based on the extracted situation and user information. The AI ​​generates an appropriate customer response conversation based on the information sent.

[0174] Input: Situation, User information

[0175] Output: Generated customer interaction dialogue (e.g., greeting, product description)

[0176] Step 5:

[0177] The server sends a response to the terminal.

[0178] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal as an HTTP response.

[0179] Input: Generated customer interaction chat (JSON format)

[0180] Output: HTTP response, data in JSON format

[0181] Step 6:

[0182] The device displays customer support chat.

[0183] The terminal receives a response from the server and parses its contents. The parsed customer interaction conversation is then displayed in the user interface (UI). The user can then interact with the customer based on the displayed conversation.

[0184] Input: JSON data, HTTP response

[0185] Output: Customer interaction talk displayed in the user interface

[0186] The above outlines the processing flow of this system's program. Through the specific actions performed at each processing step, users can efficiently acquire training modules for skill improvement and customer service dialogue appropriate to different situations.

[0187] (Application Example 1)

[0188] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] Sales staff have varying skill levels, which can lead to inconsistent customer service quality and negatively impact customer satisfaction and sales efficiency. This problem is particularly pronounced among new and less experienced staff, requiring individual skill development and training to achieve consistent, high-quality customer service. Furthermore, efficient customer service necessitates a system that provides quick and appropriate responses. In addition, there is a growing need for user-friendly systems in busy shop environments.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0191] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing device for providing the generated training modules to sales staff; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of sales staff; and an application that is installed on a smartphone or wearable device and can be easily used by sales staff on the shop floor. This ensures that the skills of sales staff are standardized reliably and quickly, enabling high-quality customer service.

[0192] "Sales staff" refers to employees who provide products and services to customers in stores or sales environments.

[0193] "Skill standardization" refers to the process of reducing the differences in skills and knowledge among multiple sales staff so that everyone can perform their duties at a consistently high level.

[0194] "Productivity improvement" refers to improving the work efficiency and output of sales staff. Specifically, it means improving the ratio of labor input to results obtained in sales operations.

[0195] "Generative artificial intelligence means" refers to artificial intelligence technology used to generate appropriate training modules based on information from sales staff.

[0196] "Information processing device" refers to a device or system for providing generated training modules and customer service scripts to sales staff.

[0197] "Talk generation artificial intelligence means" refers to artificial intelligence technology that generates necessary customer service dialogue (greetings, product descriptions, responses to questions, etc.) based on the information and situation of the sales staff.

[0198] A "smartphone" refers to a multi-functional device that combines the capabilities of a mobile phone and a computer, and can run a variety of applications.

[0199] A "wearable device" refers to a computer device that can be worn by the user. Examples include smart glasses and smartwatches.

[0200] An "application" refers to a software program that provides specific functions or services. It is installed on smartphones and wearable devices and performs various operations and provides information.

[0201] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system is operated via an application installed on a smartphone or wearable device. Specific embodiments of this system will be described in detail below.

[0202] Skill content creation and delivery

[0203] 1. User requests for skill content

[0204] Users (sales staff) make requests to retrieve their own skill content through the application's UI (user interface).

[0205] The device (smartphone or wearable device) sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0206] 2. Receiving and processing requests on the server

[0207] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0208] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0209] 3. Provision of generated skill content

[0210] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[0211] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0212] Generating and providing customer service dialogues.

[0213] 1. Customer talk requests from users

[0214] Users (sales staff) make requests through the application's UI to obtain conversational phrases appropriate for specific situations. Examples include greeting new customers or responding to product inquiries.

[0215] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0216] 2. Receiving and processing requests on the server

[0217] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0218] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[0219] 3. Provision of generated customer interaction scripts.

[0220] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[0221] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0222] Specific example

[0223] For example, consider a scenario where a new sales staff member uses the system. The staff member logs into the system to obtain their training module and requests it. The terminal sends the staff member's information to the server. The server invokes generative artificial intelligence and generates a training module based on the staff member's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to the staff member via the terminal.

[0224] Furthermore, when staff members interact with new customers in stores, they can request appropriate greetings and product descriptions. The terminal sends the situation and the staff member's name to the server. The server invokes AI for dialogue generation to create specific greetings and product descriptions. The generated dialogue is then provided to the staff member via the terminal. As a result, staff members can provide consistent, high-quality service, leading to improved customer satisfaction.

[0225] Example of a prompt

[0226] For example, here's a specific example of what to do if a new customer says, "This is my first time visiting this store":

[0227] Prompt message:

[0228] Staff name: Taro Yamada

[0229] Situation: A first-time customer has visited the store. Please generate an appropriate greeting for them.

[0230] As a result, this invention improves the skills of sales staff and standardizes the quality of customer service, thereby significantly improving sales efficiency.

[0231] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0232] Step 1:

[0233] The user (sales staff) interacts with the application's UI to make a request to retrieve their skill content. This request includes basic information such as the user's ID and name. This information is stored on the device as JSON data and later sent to the server.

[0234] Step 2:

[0235] The terminal sends the user-entered request data as a POST request to a specific endpoint on the server. The input data includes the sales staff's ID and name, and is encoded in JSON format. The terminal then waits for a response from the server.

[0236] Step 3:

[0237] The server parses the received POST request to obtain information about the sales staff. This parsing process involves parsing data in JSON format. The user information obtained as a result of the parsing is then passed to a generative artificial intelligence system within the server.

[0238] Step 4:

[0239] The server invokes generative artificial intelligence (AI) means to generate appropriate training modules based on staff information. Specifically, it evaluates staff communication skills, product knowledge, problem-solving abilities, etc., and constructs training content suitable for these skills. A generative AI model is used in this process.

[0240] Step 5:

[0241] The generated training content is encoded in JSON format and sent from the server to the terminal as a response. The terminal receives this response and expands the data on the application for display to the user. This allows the user to utilize specific training modules to strengthen their weaknesses.

[0242] Step 6:

[0243] The user then uses the application to request appropriate conversation during customer service at the store. This request data includes basic information such as the customer's situation and the user's name. This information is also prepared to be sent to the terminal in JSON format.

[0244] Step 7:

[0245] The terminal sends customer talk request data to the server. The sent data arrives at a specific endpoint on the server as a POST request. The terminal waits for the server's response and, based on the generated appropriate talk, displays it to the user.

[0246] Step 8:

[0247] The server analyzes the customer talk request and invokes an AI talk generation tool to generate customer interaction dialogue. This process creates specific dialogue based on the sales staff member's name and the situation. For example, it generates a response for the situation, "This is my first time visiting this store." An example prompt might be: "Staff name: Taro Yamada\nSituation: A first-time customer has visited the store. Please generate appropriate greeting dialogue for them."

[0248] Step 9:

[0249] The generated customer interaction chat is sent back from the server to the terminal in JSON format. The terminal receives this response and displays it to the user through the application. By using this generated chat during customer interactions, users can provide consistent, high-quality service.

[0250] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0251] This invention aims to standardize the skills and improve the productivity of sales staff, and further, it is a system that recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. This system is implemented as follows.

[0252] Skill content creation and delivery

[0253] 1. User requests for skill content

[0254] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0255] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0256] 2. Receiving and processing requests on the server

[0257] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0258] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0259] 3. Generation of training content using generative artificial intelligence methods

[0260] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[0261] The generated training modules are tailored to the user's emotions. For example, if the user is feeling stressed, a training module including relaxation techniques will be generated.

[0262] 4. Provision of generated skill content

[0263] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[0264] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0265] Generating and providing customer service dialogues.

[0266] 1. Customer talk requests from users

[0267] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0268] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0269] 2. Receiving and processing requests on the server

[0270] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0271] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0272] 3. Dialogue generation using AI-powered dialogue generation tools

[0273] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[0274] The generated customer service messages are tailored based on perceived emotions. For example, if a user is feeling anxious, a concise and reassuring message will be generated.

[0275] 4. Providing generated customer interaction scripts.

[0276] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0277] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0278] Specific example

[0279] For example, consider the scenario where a new sales staff member, Staff A, uses the system. Staff A logs into the system to obtain their training module and requests the training module. The terminal sends Staff A's information to the server. The server calls the generative AI and the emotion engine, and based on Staff A's communication skills, product knowledge, and problem-solving abilities, generates a training module that takes into account Staff A's emotions. For example, if Staff A is feeling stressed, a module including relaxation techniques is provided. The generated training module is provided to Staff A via the terminal.

[0280] Also, in the scenario where Staff A interacts with new customers at the store, Staff A requests appropriate greeting texts and product description texts. The terminal sends the situation and Staff A's name to the server. The server calls the talk generation AI and the emotion engine, and generates specific greeting texts and product description texts according to Staff A's emotional state. For example, if Staff A is nervous, concise and reassuring talk is generated. The generated talk is provided to Staff A via the terminal. As a result, Staff A can provide a consistent and high-quality response, improving customer satisfaction.

[0281] Thereby, the present invention realizes the improvement of the skills of sales staff and the homogenization of the quality of customer response, enabling the improvement of productivity. Also, by introducing the emotion engine, flexible response according to the emotional state of the staff becomes possible, and further improvement of business efficiency is expected.

[0282] The following describes the processing flow.

[0283] Generation and provision of skill content

[0284] Step 1:

[0285] The user (sales staff) makes a request to obtain their skill content via the UI (user interface).

[0286] Step 2:

[0287] The terminal sends this request to the server as data in JSON format. The request data includes basic information such as the user's ID and name.

[0288] Step 3:

[0289] The server receives the POST request at a specific endpoint and analyzes the content as JSON. Through this analysis, the staff's information is obtained.

[0290] Step 4:

[0291] The server analyzes the user's sentiment using a sentiment engine. The sentiment engine recognizes sentiment by analyzing the user's facial expressions, voice tones, gestures, etc.

[0292] Step 5:

[0293] The server calls generative AI means based on the staff information and the recognized sentiment. The generative AI means analyzes basic skills such as, for example, the communication ability, product knowledge, and problem-solving ability of the sales staff, and generates an appropriate training module.

[0294] Step 6:

[0295] The server adjusts the generated training module according to the sentiment. For example, when the user is feeling stressed, a training module including relaxation techniques is generated.

[0296] Step 7:

[0297] The server receives the skill content returned from the generative AI means and returns it to the terminal as a JSON-formatted response.

[0298] Step 8:

[0299] The terminal receives this response and provides the user with an appropriate training module. As a result, the user can receive specific training on their weaknesses and skills that need to be strengthened.

[0300] Generation and provision of customer service conversations

[0301] Step 1:

[0302] The user (sales staff) makes a request via the UI to obtain a conversation suitable for a specific situation. For example, greetings to new customers or responses to inquiries about products.

[0303] Step 2:

[0304] The terminal sends this request to the server in JSON format. The request data includes the situation and staff information.

[0305] Step 3:

[0306] The server receives the POST request at a specific endpoint and analyzes the content as JSON. Through this analysis, the situation and staff information are obtained.

[0307] Step 4:

[0308] The server analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tones, gestures, etc.

[0309] Step 5:

[0310] The server calls the talk generation artificial intelligence means based on the situation, staff information, and recognized emotions. The talk generation artificial intelligence means generates customer service conversations (e.g., greeting sentences, product description sentences, question response sentences) using the name of the sales staff.

[0311] Step 6:

[0312] The server adjusts the generated customer interaction dialogue based on the user's emotions. For example, if the user is feeling anxious, a concise and reassuring dialogue will be generated.

[0313] Step 7:

[0314] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0315] Step 8:

[0316] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0317] (Example 2)

[0318] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0319] Traditional sales staff training systems struggled to provide appropriate training modules and customer service phrases tailored to staff skills and specific situations. Furthermore, training and interactions that disregarded staff emotional states led to decreased productivity and difficulty in improving customer satisfaction. A system was needed to address these challenges, standardize sales staff skills, improve productivity, and enhance customer satisfaction.

[0320] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0321] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing means for providing the generated training modules to the sales staff; an emotion analysis means for recognizing the emotions of the sales staff and adjusting the training modules; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of the sales staff; and an information processing means for providing the generated customer service talk to the sales staff. This enables sales staff to perform appropriate training and customer service tailored to their own emotional state.

[0322] "Sales staff" is a general term for employees who are responsible for selling products.

[0323] "Skill standardization" is the process of reducing differences in staff abilities and skills in specific tasks and bringing them to a uniform level.

[0324] "Productivity improvement" is a process that aims to produce more results or deliverables with a given amount of resources and time.

[0325] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules and content based on specific data and information.

[0326] "Information processing device" is a general term for computer systems that have the ability to receive, analyze, convert, and transmit data.

[0327] "Emotional analysis methods" refer to technologies that analyze a user's emotional state through their facial expressions, voice tone, input speed, and other factors.

[0328] "Conversation generation artificial intelligence means" refers to artificial intelligence technology that automatically generates conversations and texts based on specific conditions and information.

[0329] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system recognizes the emotions of sales staff and generates and provides training modules and customer service dialogues based on those emotions, thereby improving staff skills and the quality of customer service.

[0330] Hardware and software to be used

[0331] This system uses the following hardware and software:

[0332] Server: Responsible for receiving requests, analyzing data, and executing generative artificial intelligence and sentiment analysis.

[0333] Terminal: Responsible for sending user requests and displaying generated content.

[0334] Generative artificial intelligence models: These include AI models from OpenAI® and Google®, used to automatically generate training modules for improving the skills of sales staff.

[0335] Emotion Analysis Engine: Uses technologies to analyze user emotions, such as Microsoft® Azure® Emotion API and Google Cloud Vision API.

[0336] Dialogue generation artificial intelligence models: Natural language processing models such as GPT-3 (registered trademark) and BERT are used to automatically generate customer response dialogue tailored to the user's situation.

[0337] System Operation Overview

[0338] The user logs into the system and submits a request for a training module to improve their skills. The terminal sends this request to the server in JSON format. The server receives and parses the request and invokes an emotion analysis engine to recognize the user's emotions. After the emotion analysis engine analyzes the user's emotional state, the server invokes a generative artificial intelligence model based on that information and generates an appropriate training module. This training module is customized according to the user's emotional state (e.g., if the user is feeling stressed, it will include relaxation techniques). The generated training module is then provided to the user via the terminal.

[0339] For example, consider a case where a new sales staff member requests a training module to improve their communication skills. When the user enters information into a form and clicks the submit button, the device generates JSON data in the following format:

[0340] json

[0341] {

[0342] "userId": "A12345",

[0343] "name": "Mr. A",

[0344] "skillRequest": "Communication skills"

[0345] }

[0346] The server receives this request and uses its emotion analysis engine to analyze whether the user is experiencing stress. It then calls a generative AI model to generate a training module like the following:

[0347] json

[0348] {

[0349] "module": "Communication Basics",

[0350] "exercises": ["Conversation simulation", "Listening practice"]

[0351] "addedModule": "Relaxation Techniques"

[0352] }

[0353] This information is sent back to the device and provided to the user.

[0354] Furthermore, if a user requests customer service dialogue in a specific situation, the process follows a similar flow. For example, if a user requests a "greeting message for a new customer," the device sends a request to the server as follows:

[0355] json

[0356] {

[0357] "userId": "A12345",

[0358] "name": "Mr. A",

[0359] "situation": "Greetings to new customers"

[0360] }

[0361] The server uses an emotion analysis engine to analyze the user's emotional state and invokes a speech generation AI model to generate the following speech:

[0362] json

[0363] {

[0364] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[0365] }

[0366] This message is sent back to the device and displayed to the user.

[0367] Example of a prompt

[0368] The following is an example of a prompt message sent to an AI model:

[0369] For training modules:

[0370] "New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing."

[0371] In the case of customer service conversations:

[0372] "New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message."

[0373] As described above, this system improves the skills and productivity of sales staff. Furthermore, by enabling flexible responses tailored to the user's emotional state, it contributes to increased customer satisfaction.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] The user enters and submits a skill content request.

[0377] Input: The user logs into the system and enters request information for skill improvement (e.g., name, ID, skill area) into the UI input form.

[0378] Specific action: The user enters information and clicks the "Submit" button.

[0379] Output: The terminal converts the input information into JSON format and generates request data like this:

[0380] json

[0381] {

[0382] "userId": "A12345",

[0383] "name": "Mr. A",

[0384] "skillRequest": "Communication skills"

[0385] }

[0386] Step 2:

[0387] The terminal sends a request to the server.

[0388] Input: Request data in JSON format containing information entered by the user.

[0389] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[0390] Output: Request data in JSON format is sent to the server.

[0391] Step 3:

[0392] The server receives the request and parses the data.

[0393] Input: Request data in JSON format sent from the terminal.

[0394] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and skill request information.

[0395] Output: Analyzed user information is obtained.

[0396] Step 4:

[0397] The server invokes an emotion analysis engine to analyze the user's emotions.

[0398] Input: Analyzed user information.

[0399] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[0400] Output: The user's emotional state (e.g., stress, tension) is obtained.

[0401] Step 5:

[0402] The server invokes a generative artificial intelligence model and generates training content.

[0403] Input: User information and sentiment analysis results.

[0404] Specific operation: The server sends this information to the generative artificial intelligence model in the form of prompt statements. For example, the following prompt statements are used:

[0405] text

[0406] New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing.

[0407] Output: A customized training module is obtained from the generative artificial intelligence model. Example:

[0408] json

[0409] {

[0410] "module": "Communication Basics",

[0411] "exercises": ["Conversation simulation", "Listening practice"]

[0412] "addedModule": "Relaxation Techniques"

[0413] }

[0414] Step 6:

[0415] The server sends the generated training module to the terminal.

[0416] Input: The generated training module.

[0417] Specific operation: The server returns the training module to the terminal as a JSON response.

[0418] Output: JSON-formatted response data received by the terminal.

[0419] Step 7:

[0420] The device provides the user with a training module.

[0421] Input: Training module received from the server.

[0422] Specific operation: The device analyzes this data and presents it to the user visually. The screen displays a "Start" button and training content.

[0423] Output: An environment is created where users can visually check and run training modules.

[0424] Step 8:

[0425] The user enters and submits a customer support chat request.

[0426] Input: Request information for customer service dialogue in a specific situation (e.g., situation, staff name).

[0427] Specific action: The user enters information and clicks the "Submit" button.

[0428] Output: The terminal converts the input information into JSON format and generates request data like this:

[0429] json

[0430] {

[0431] "userId": "A12345",

[0432] "name": "Mr. A",

[0433] "situation": "Greetings to new customers"

[0434] }

[0435] Step 9:

[0436] The terminal sends a request to the server.

[0437] Input: Request data in JSON format containing information entered by the user.

[0438] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[0439] Output: Request data in JSON format is sent to the server.

[0440] Step 10:

[0441] The server receives the request and parses the data.

[0442] Input: Request data in JSON format sent from the terminal.

[0443] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and status information.

[0444] Output: Analyzed situation and staff information are obtained.

[0445] Step 11:

[0446] The server invokes an emotion analysis engine to analyze the user's emotions.

[0447] Input: Analyzed situation and staff information.

[0448] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[0449] Output: The user's emotional state (e.g., tension) is obtained.

[0450] Step 12:

[0451] The server invokes an artificial intelligence mechanism for generating conversational responses, which then generates appropriate customer service dialogue.

[0452] Input: Situation information and emotion analysis results.

[0453] Specific operation: The server sends this information to the AI ​​talk generation model in the form of prompt statements. For example, the following prompt statements are used:

[0454] text

[0455] New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message.

[0456] Output: Customized customer service dialogue is obtained from the AI ​​talk generation model. Example:

[0457] json

[0458] {

[0459] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[0460] }

[0461] Step 13:

[0462] The server sends the generated customer interaction message to the terminal.

[0463] Input: Generated customer interaction chat.

[0464] Specific operation: The server sends the customer interaction conversation back to the terminal as a JSON response.

[0465] Output: JSON-formatted response data received by the terminal.

[0466] Step 14:

[0467] The terminal provides the user with customer service dialogue.

[0468] Input: Customer interaction messages received from the server.

[0469] Specific operation: The device analyzes this data and presents it to the user visually. The generated chat content is displayed on the screen.

[0470] Output: An environment is created where users can visually review customer interaction scripts and use them in actual customer interactions.

[0471] (Application Example 2)

[0472] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0473] Sales staff's customer service varies depending on their individual skills and emotional states, making it difficult to achieve consistently high-quality service. Furthermore, training and follow-up tailored to each sales staff member's emotional state may be insufficient. Therefore, there is a need for skill standardization and increased productivity.

[0474] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generative artificial intelligence means for generating training modules based on sales staff information, an information processing device for providing the generated training modules to the sales staff, a talk generation artificial intelligence means for generating customer service talk according to the sales staff's information and situation, an information processing device for providing the generated customer service talk to the sales staff, an emotion recognition means for recognizing the emotional state of the sales staff, and an emotion adjustment means for adjusting the training modules and customer service talk based on information obtained from the emotion recognition means. This enables flexible responses and skill standardization according to the emotional state of the sales staff.

[0475] "Sales staff" are store employees whose primary role is to introduce and sell products and services to customers.

[0476] "Skill standardization" means ensuring that all sales staff have the same level of knowledge and ability.

[0477] "Productivity improvement" refers to increasing the efficiency of operations so that more results can be achieved with fewer resources.

[0478] A "system" is a collection of devices and methods designed to improve the skills of sales staff and enhance the quality of customer service.

[0479] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules based on information from sales staff.

[0480] An "information processing device" is a device or system that analyzes collected data and provides sales staff with the information and skill content they need.

[0481] "AI-generated dialogue means" refers to artificial intelligence technology that automatically generates appropriate customer service dialogue based on the information and situation of sales staff.

[0482] "Emotion recognition means" refers to technology that analyzes the facial expressions and voice of sales staff to recognize their emotional state.

[0483] "Emotional adjustment techniques" are technologies for appropriately adjusting training modules and customer service dialogues based on the recognized emotional state of sales staff.

[0484] "Users" refer to sales staff who actually use this system to acquire training modules and customer service scripts.

[0485] A "terminal" is a device (such as smart glasses, smartphones, or head-mounted displays) that a user uses to access the system and obtain training modules and customer service dialogues.

[0486] A "server" is a computer system that manages the entire system, including generative artificial intelligence means and talk generation artificial intelligence means, and performs the necessary data processing.

[0487] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff, and further, it recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. Specifically, it is realized through the following configuration and processing procedure.

[0488] System Overview

[0489] The system of the present invention includes the following main hardware and software.

[0490] Hardware:

[0491] Smart glasses (with camera and display)

[0492] Servers (cloud servers and local servers)

[0493] software:

[0494] Python

[0495] OpenCV (image processing library)

[0496] Requests (HTTP Request Library)

[0497] Program processing

[0498] emotion recognition

[0499] The system uses the camera on smart glasses attached to the device to acquire a facial image of the user (sales staff). The acquired facial image is analyzed using the OpenCV image processing library, and the user's emotional state is determined by emotion recognition. Emotional states include, for example, "tension," "stress," and "reassurance."

[0500] Training module generation

[0501] Based on emotion recognition results and information about the sales staff, a generative artificial intelligence (AI) system on the server generates appropriate training modules. This AI system creates training content considering the sales staff's communication skills, product knowledge, and problem-solving abilities. Depending on the emotional state, training modules including, for example, relaxation techniques are generated.

[0502] Generating customer service dialogues

[0503] To address specific situations requested by users, an AI-powered dialogue generation system on the server generates customer service dialogue based on emotion recognition results and sales staff information. This system creates appropriate greetings and product descriptions according to the sales staff's name and situation information. If the emotional state is tense, a concise and reassuring dialogue is provided.

[0504] Information provision

[0505] The generated training modules and customer service dialogues are provided to the user via a terminal. They are displayed on the smart glasses' screen and can be used by the user in real time.

[0506] Specific example

[0507] For example, consider a scenario where a new sales staff member uses the system. Imagine the sales staff member wearing smart glasses and greeting a new customer. If the server detects that the sales staff member is nervous, it will provide a generated conversation based on prompts such as the following:

[0508] Example of a prompt:

[0509] Based on "Person A's nervous emotions," generate a "greeting speech for a new customer." Provide a simple greeting that will put the customer at ease.

[0510] The smart glasses display a concise and reassuring message such as, "Hello, what are you looking for today?" This enables sales staff to provide consistent, high-quality service, improving customer satisfaction.

[0511] The system of this invention allows sales staff to receive appropriate training and customer support in real time, tailored to their own emotional state, resulting in standardized skills and improved productivity.

[0512] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0513] Step 1:

[0514] The user puts on the smart glasses and presses the start button. The smart glasses' camera acquires a facial image. The facial image is captured in real time and sent to the terminal. The input is the user's facial image, and the output is the transmission of the facial image to the terminal. This process involves enabling the camera function, capturing a facial image, and sending it.

[0515] Step 2:

[0516] The device analyzes facial images acquired from the camera using OpenCV and extracts facial feature points. Next, it performs emotion recognition based on these feature points. The input is the acquired facial image, and the output is the recognized emotional state (e.g., "stressed"). This process uses image processing and a machine learning model for emotion recognition.

[0517] Step 3:

[0518] The device sends the recognized emotional state and basic user information (ID and name) to the server in JSON format. The input is the emotional state and user information, and the output is the transmission of JSON data to the server. This process involves data format conversion and sending an HTTP request.

[0519] Step 4:

[0520] The server parses the received JSON data to obtain the user's emotional state and basic information. Based on the parsed data, it invokes a generative artificial intelligence system to generate an appropriate training module. The input is the received JSON data, and the output is the generated training module. This process involves data analysis and invoking an AI model.

[0521] Step 5:

[0522] The server uses a separate AI-powered talk generation mechanism to generate customer service dialogue based on the user's emotional state and basic information. The input consists of user information, situation information, and emotional state, while the output is the generated customer service dialogue. This process involves data analysis and AI model calls.

[0523] Step 6:

[0524] The server returns the generated training module and customer interaction talk to the terminal in JSON format. The input is the generated training module and customer interaction talk, and the output is the JSON response to the terminal. This process involves data format conversion and sending an HTTP response.

[0525] Step 7:

[0526] The terminal analyzes the training module and customer interaction dialogue received from the server and displays them on the smart glasses' display. The input is JSON data from the server, and the output is the training module and customer interaction dialogue displayed on the screen. This process involves data analysis and display operations.

[0527] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0528] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0529] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0530] [Second Embodiment]

[0531] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0532] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0533] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0534] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0535] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0536] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0537] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0538] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0539] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0540] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0541] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0542] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0543] This invention is a system aimed at standardizing the skills of sales staff and improving productivity. This system is implemented as follows.

[0544] Skill content creation and delivery

[0545] 1. User requests for skill content

[0546] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0547] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0548] 2. Server receiving and processing requests

[0549] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0550] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0551] 3. Provision of generated skill content

[0552] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[0553] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0554] Generating and providing customer service dialogues

[0555] 1. Customer talk requests from users

[0556] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0557] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0558] 2. Server receiving and processing requests

[0559] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0560] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[0561] 3. Provision of generated customer interaction scripts.

[0562] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[0563] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0564] Specific example

[0565] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and generates a training module based on A's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to A via the terminal.

[0566] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI to generate specific greetings and product descriptions. The generated talks are then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[0567] As a result, the present invention can improve the skills of sales staff and standardize the quality of customer service, thereby significantly improving sales efficiency.

[0568] The following describes the processing flow.

[0569] Skill content creation and delivery

[0570] Step 1:

[0571] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0572] Step 2:

[0573] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0574] Step 3:

[0575] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0576] Step 4:

[0577] The server invokes a generative artificial intelligence (AI) system based on staff information. The AI ​​system analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0578] Step 5:

[0579] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[0580] Step 6:

[0581] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0582] Generating and providing customer service dialogues

[0583] Step 1:

[0584] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0585] Step 2:

[0586] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0587] Step 3:

[0588] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0589] Step 4:

[0590] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The talk generation AI mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[0591] Step 5:

[0592] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0593] Step 6:

[0594] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0595] (Example 1)

[0596] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0597] Standardizing the skills and improving the productivity of sales staff are important challenges for many companies. In particular, since sales staff skills depend on individual experience and knowledge, standardizing them is difficult. Furthermore, providing high-quality customer service tailored to each situation is also not easy. Therefore, there has been a need for efficient and effective means to standardize the skills of sales staff and improve productivity.

[0598] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0599] In this invention, the server includes terminal means for receiving requests from users, converting information into JSON format and sending it to the server; generative artificial intelligence means for analyzing the JSON data sent to the server, calling a generation AI model based on the analysis results and generating an appropriate training module; means for sending and displaying the generated training module again as a JSON response to the terminal; means for receiving customer service talk requests from users, analyzing data including situation and staff information, calling a talk generation artificial intelligence based on the analysis results; and means for sending and displaying the customer service talk generated by the talk generation artificial intelligence as a JSON response to the terminal. This enables the standardization of sales staff skills and high-quality customer service tailored to the situation.

[0600] A "terminal device" is a device that has the function of receiving requests from users, converting the information into JSON format, and sending it to the server.

[0601] A "generative artificial intelligence means" is a system that includes artificial intelligence that analyzes JSON data sent to a server and generates appropriate training modules based on the analysis results.

[0602] A "generative AI model" is a general term for artificial intelligence algorithms that generate training modules and customer service dialogues based on the skills and abilities of sales staff.

[0603] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a standard for organizing data into a data structure that is easy for both humans and machines to read.

[0604] A "talk generation artificial intelligence means" is a system that includes artificial intelligence that analyzes user request data and generates appropriate customer response talk based on the situation and staff information.

[0605] A "prompt sentence" is an input sentence given to a generative AI model to enable it to perform predictions or generation.

[0606] "Response" is a term that refers to the response data sent from a server to a terminal.

[0607] A "training module" is a collection of learning programs and materials designed to improve the skills of sales staff.

[0608] "Customer service dialogue" refers to phrases and explanations used for customer service in specific situations.

[0609] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system utilizes generative artificial intelligence means and talk generation artificial intelligence means to improve the skills of sales staff and the quality of customer service.

[0610] Skill content creation and delivery

[0611] First, users request training modules through the system's UI (user interface) to improve their skills. When a user enters the necessary information (ID, name, etc.) into the request form and clicks the submit button, the device converts this input data into JSON format and sends it to the server.

[0612] The server receives POST requests at a specific endpoint and parses the received data in JSON format. Next, it extracts user information (ID, name, etc.) from the parsed data and uses this to send a prompt to a generative artificial intelligence (e.g., the GPT-4 API). The generative AI generates a training module and returns a response to the server.

[0613] The server compiles the generated training modules into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then view the displayed training modules and work to improve their skills.

[0614] Generating and providing customer service dialogues

[0615] Next, the user makes a request via the UI to retrieve a conversation appropriate for a specific customer interaction situation. The user enters the situation (e.g., new customer interaction, product explanation) and their own information, and clicks the submit button, at which point the device sends this data to the server in JSON format.

[0616] The server receives POST requests at a specific endpoint and parses the data in JSON format. It extracts situation and staff information from the parsed data and uses this to send prompt messages to a talk generation artificial intelligence (e.g., GPT-4 API). The talk generation artificial intelligence generates appropriate customer service dialogue and returns a response to the server.

[0617] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then interact with the customer based on the displayed conversation.

[0618] Specific example

[0619] For example, consider the process by which a new sales staff member obtains their training module. This sales staff member logs into the system, enters their ID and name into the request form, and then clicks the submit button. The terminal converts this information into JSON format and sends it to the server. The server receives and analyzes this data, then calls a generative artificial intelligence (GPT-4) to generate a training module. The generated module is sent to the terminal as a JSON response and displayed.

[0620] Furthermore, when a new sales staff member interacts with a new customer in the store, they can request appropriate customer service dialogue. Once the staff member inputs the situation and submits the request, the terminal converts the data into JSON format and sends it to the server. The server receives and analyzes the data, invokes the dialogue generation artificial intelligence (GPT-4), and generates appropriate dialogue. The generated dialogue is then sent to the terminal as a JSON response and displayed.

[0621] Example of a prompt

[0622] An example of a prompt message in a skill content request is as follows:

[0623] "Generate training modules to improve product knowledge and problem-solving skills based on user IDs and names."

[0624] An example of a prompt in a customer talk request is as follows:

[0625] "Please generate a greeting message for new customers based on their user ID and name."

[0626] The above describes specific embodiments for carrying out the present invention. This system effectively enables the standardization of sales staff skills and improvement of productivity.

[0627] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0628] Skill content creation and delivery

[0629] Step 1:

[0630] The user makes a request

[0631] The user logs into the application to obtain the training module and enters the required information (ID, name, etc.) into the request form. The user then clicks the submit button on the form.

[0632] Input: User ID, name, and other information

[0633] Output: Event when the submit button was clicked

[0634] Step 2:

[0635] The device sends the request to the server.

[0636] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[0637] Input: User ID, name, and other information

[0638] Output: JSON data, HTTP POST request

[0639] Step 3:

[0640] The server receives the request.

[0641] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[0642] Input: JSON data, HTTP POST request

[0643] Output: Parsed user ID, name, and other information

[0644] Step 4:

[0645] The server invokes a generative artificial intelligence.

[0646] The server sends a prompt message to a generative artificial intelligence (e.g., GPT-4) based on the extracted user information. The generative artificial intelligence then generates an appropriate training module based on the information received.

[0647] Input: User ID, name, and other information

[0648] Output: The generated training module (e.g., a training module on product knowledge)

[0649] Step 5:

[0650] The server sends a response to the terminal.

[0651] The server compiles the generated training modules into a JSON response and sends it back to the terminal as an HTTP response.

[0652] Input: Generated training module (in JSON format)

[0653] Output: HTTP response, data in JSON format

[0654] Step 6:

[0655] The device displays skill content.

[0656] The terminal receives a response from the server and parses its contents. It then displays the parsed training module in the user interface (UI).

[0657] Users can view the displayed skill content and begin training.

[0658] Input: JSON data, HTTP response

[0659] Output: Training modules displayed in the user interface

[0660] Generating and providing customer service dialogues

[0661] Step 1:

[0662] The user makes a request

[0663] The user fills out a request form in the application to obtain a conversation appropriate for a specific situation. For example, they enter the situation (e.g., new customer support, product explanation) and their own information. The user then clicks the submit button on the form.

[0664] Input: Situation, User information

[0665] Output: Event when the submit button was clicked

[0666] Step 2:

[0667] The device sends the request to the server.

[0668] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[0669] Input: Situation, User information

[0670] Output: JSON data, HTTP POST request

[0671] Step 3:

[0672] The server receives the request.

[0673] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[0674] Input: JSON data, HTTP POST request

[0675] Output: Parsed situation, user information

[0676] Step 4:

[0677] The server invokes the AI ​​for generating speech.

[0678] The server sends a prompt message to the AI ​​that generates the conversation (e.g., GPT-4) based on the extracted situation and user information. The AI ​​generates an appropriate customer response conversation based on the information sent.

[0679] Input: Situation, User information

[0680] Output: Generated customer interaction dialogue (e.g., greeting, product description)

[0681] Step 5:

[0682] The server sends a response to the terminal.

[0683] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal as an HTTP response.

[0684] Input: Generated customer interaction chat (JSON format)

[0685] Output: HTTP response, data in JSON format

[0686] Step 6:

[0687] The device displays customer support chat.

[0688] The terminal receives a response from the server and parses its contents. The parsed customer interaction conversation is then displayed in the user interface (UI). The user can then interact with the customer based on the displayed conversation.

[0689] Input: JSON data, HTTP response

[0690] Output: Customer interaction talk displayed in the user interface

[0691] The above outlines the processing flow of this system's program. Through the specific actions performed at each processing step, users can efficiently acquire training modules for skill improvement and customer service dialogue appropriate to different situations.

[0692] (Application Example 1)

[0693] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0694] Sales staff have varying skill levels, which can lead to inconsistent customer service quality and negatively impact customer satisfaction and sales efficiency. This problem is particularly pronounced among new and less experienced staff, requiring individual skill development and training to achieve consistent, high-quality customer service. Furthermore, efficient customer service necessitates a system that provides quick and appropriate responses. In addition, there is a growing need for user-friendly systems in busy shop environments.

[0695] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0696] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing device for providing the generated training modules to sales staff; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of sales staff; and an application that is installed on a smartphone or wearable device and can be easily used by sales staff on the shop floor. This ensures that the skills of sales staff are standardized reliably and quickly, enabling high-quality customer service.

[0697] "Sales staff" refers to employees who provide products and services to customers in stores or sales environments.

[0698] "Skill standardization" refers to the process of reducing the differences in skills and knowledge among multiple sales staff so that everyone can perform their duties at a consistently high level.

[0699] "Productivity improvement" refers to improving the work efficiency and output of sales staff. Specifically, it means improving the ratio of labor input to results obtained in sales operations.

[0700] "Generative artificial intelligence means" refers to artificial intelligence technology used to generate appropriate training modules based on information from sales staff.

[0701] "Information processing device" refers to a device or system for providing generated training modules and customer service scripts to sales staff.

[0702] "AI-generated dialogue means" refers to artificial intelligence technology that generates the necessary dialogue (greetings, product descriptions, responses to questions, etc.) for customer service based on the information and situation of the sales staff.

[0703] A "smartphone" refers to a multi-functional device that combines the capabilities of a mobile phone and a computer, and can run a variety of applications.

[0704] A "wearable device" refers to a computer device that can be worn by the user. Examples include smart glasses and smartwatches.

[0705] An "application" refers to a software program that provides specific functions or services. It is installed on smartphones and wearable devices and performs various operations and provides information.

[0706] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system is operated via an application installed on a smartphone or wearable device. Specific embodiments of this system will be described in detail below.

[0707] Skill content creation and delivery

[0708] 1. User requests for skill content

[0709] Users (sales staff) make requests to retrieve their own skill content through the application's UI (user interface).

[0710] The device (smartphone or wearable device) sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0711] 2. Server receiving and processing requests

[0712] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0713] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[0714] 3. Provision of generated skill content

[0715] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[0716] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0717] Generating and providing customer service dialogues

[0718] 1. Customer talk requests from users

[0719] Users (sales staff) make requests through the application's UI to obtain conversational phrases appropriate for specific situations. Examples include greeting new customers or responding to product inquiries.

[0720] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0721] 2. Server receiving and processing requests

[0722] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0723] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[0724] 3. Provision of generated customer interaction scripts.

[0725] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[0726] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0727] Specific example

[0728] For example, consider a scenario where a new sales staff member uses the system. The staff member logs into the system to obtain their training module and requests it. The terminal sends the staff member's information to the server. The server invokes generative artificial intelligence and generates a training module based on the staff member's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to the staff member via the terminal.

[0729] Furthermore, when staff members interact with new customers in stores, they can request appropriate greetings and product descriptions. The terminal sends the situation and the staff member's name to the server. The server invokes AI for dialogue generation to create specific greetings and product descriptions. The generated dialogue is then provided to the staff member via the terminal. As a result, staff members can provide consistent, high-quality service, leading to improved customer satisfaction.

[0730] Example of a prompt

[0731] For example, here's a specific example of what to do if a new customer says, "This is my first time visiting this store":

[0732] Prompt message:

[0733] Staff name: Taro Yamada

[0734] Situation: A first-time customer has visited the store. Please generate an appropriate greeting for them.

[0735] As a result, this invention improves the skills of sales staff and standardizes the quality of customer service, thereby significantly improving sales efficiency.

[0736] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0737] Step 1:

[0738] The user (sales staff) interacts with the application's UI to make a request to retrieve their skill content. This request includes basic information such as the user's ID and name. This information is stored on the device as JSON data and later sent to the server.

[0739] Step 2:

[0740] The terminal sends the user-entered request data as a POST request to a specific endpoint on the server. The input data includes the sales staff's ID and name, and is encoded in JSON format. The terminal then waits for a response from the server.

[0741] Step 3:

[0742] The server parses the received POST request to obtain information about the sales staff. This parsing process involves parsing data in JSON format. The user information obtained as a result of the parsing is then passed to a generative artificial intelligence system within the server.

[0743] Step 4:

[0744] The server invokes generative artificial intelligence (AI) means to generate appropriate training modules based on staff information. Specifically, it evaluates staff communication skills, product knowledge, problem-solving abilities, etc., and constructs training content suitable for these skills. A generative AI model is used in this process.

[0745] Step 5:

[0746] The generated training content is encoded in JSON format and sent from the server to the terminal as a response. The terminal receives this response and expands the data on the application for display to the user. This allows the user to utilize specific training modules to strengthen their weaknesses.

[0747] Step 6:

[0748] The user then uses the application to request appropriate conversation during customer service at the store. This request data includes basic information such as the customer's situation and the user's name. This information is also prepared to be sent to the terminal in JSON format.

[0749] Step 7:

[0750] The terminal sends customer talk request data to the server. The sent data arrives at a specific endpoint on the server as a POST request. The terminal waits for the server's response and, based on the generated appropriate talk, displays it to the user.

[0751] Step 8:

[0752] The server analyzes the customer talk request and invokes an AI talk generation tool to generate customer interaction dialogue. This process creates specific dialogue based on the sales staff member's name and the situation. For example, it generates a response for the situation, "This is my first time visiting this store." An example prompt might be: "Staff name: Taro Yamada\nSituation: A first-time customer has visited the store. Please generate appropriate greeting dialogue for them."

[0753] Step 9:

[0754] The generated customer interaction chat is sent back from the server to the terminal in JSON format. The terminal receives this response and displays it to the user through the application. By using this generated chat during customer interactions, users can provide consistent, high-quality service.

[0755] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0756] This invention aims to standardize the skills and improve the productivity of sales staff, and further, it is a system that recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. This system is implemented as follows.

[0757] Skill content creation and delivery

[0758] 1. User requests for skill content

[0759] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0760] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0761] 2. Server receiving and processing requests

[0762] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0763] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0764] 3. Generation of training content using generative artificial intelligence methods

[0765] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[0766] The generated training modules are tailored to the user's emotions. For example, if the user is feeling stressed, a training module including relaxation techniques will be generated.

[0767] 4. Provision of generated skill content

[0768] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[0769] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0770] Generating and providing customer service dialogues

[0771] 1. Customer talk requests from users

[0772] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0773] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[0774] 2. Server receiving and processing requests

[0775] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0776] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0777] 3. Dialogue generation using AI-powered dialogue generation tools

[0778] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[0779] The generated customer service messages are tailored based on perceived emotions. For example, if a user is feeling anxious, a concise and reassuring message will be generated.

[0780] 4. Providing generated customer interaction scripts.

[0781] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0782] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0783] Specific example

[0784] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and an emotion engine to generate a training module that takes A's emotions into account, based on A's communication skills, product knowledge, and problem-solving abilities. For example, if A is feeling stressed, a module including relaxation techniques will be provided. The generated training module is then delivered to A via the terminal.

[0785] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI and an emotion engine to generate specific greetings and product descriptions tailored to Person A's emotional state. For example, if Person A is nervous, a concise and reassuring message is generated. The generated message is then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[0786] This invention enables improved sales staff skills and standardized customer service quality, thereby increasing productivity. Furthermore, the introduction of an emotion engine allows for flexible responses tailored to the emotional state of staff, leading to further improvements in operational efficiency.

[0787] The following describes the processing flow.

[0788] Skill content creation and delivery

[0789] Step 1:

[0790] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[0791] Step 2:

[0792] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[0793] Step 3:

[0794] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[0795] Step 4:

[0796] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0797] Step 5:

[0798] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[0799] Step 6:

[0800] The server adjusts the generated training modules based on the user's emotions. For example, if the user is feeling stressed, a training module that includes relaxation techniques will be generated.

[0801] Step 7:

[0802] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[0803] Step 8:

[0804] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[0805] Generating and providing customer service dialogues

[0806] Step 1:

[0807] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[0808] Step 2:

[0809] The terminal sends this request to the server in JSON format. The request data includes situation and staff information.

[0810] Step 3:

[0811] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[0812] Step 4:

[0813] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[0814] Step 5:

[0815] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[0816] Step 6:

[0817] The server adjusts the generated customer interaction dialogue based on the user's emotions. For example, if the user is feeling anxious, a concise and reassuring dialogue will be generated.

[0818] Step 7:

[0819] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[0820] Step 8:

[0821] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[0822] (Example 2)

[0823] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0824] Traditional sales staff training systems struggled to provide appropriate training modules and customer service phrases tailored to staff skills and specific situations. Furthermore, training and interactions that disregarded staff emotional states led to decreased productivity and difficulty in improving customer satisfaction. A system was needed to address these challenges, standardize sales staff skills, improve productivity, and enhance customer satisfaction.

[0825] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0826] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing means for providing the generated training modules to the sales staff; an emotion analysis means for recognizing the emotions of the sales staff and adjusting the training modules; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of the sales staff; and an information processing means for providing the generated customer service talk to the sales staff. This enables sales staff to perform appropriate training and customer service tailored to their own emotional state.

[0827] "Sales staff" is a general term for employees who are responsible for selling products.

[0828] "Skill standardization" is the process of reducing differences in staff abilities and skills in specific tasks and bringing them to a uniform level.

[0829] "Productivity improvement" is a process that aims to produce more results or deliverables with a given amount of resources and time.

[0830] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules and content based on specific data and information.

[0831] "Information processing device" is a general term for computer systems that have the ability to receive, analyze, convert, and transmit data.

[0832] "Emotional analysis methods" refer to technologies that analyze a user's emotional state through their facial expressions, voice tone, input speed, and other factors.

[0833] "Conversation generation artificial intelligence means" refers to artificial intelligence technology that automatically generates conversations and texts based on specific conditions and information.

[0834] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system recognizes the emotions of sales staff and generates and provides training modules and customer service dialogues based on those emotions, thereby improving staff skills and the quality of customer service.

[0835] Hardware and software to be used

[0836] This system uses the following hardware and software:

[0837] Server: Responsible for receiving requests, analyzing data, and executing generative artificial intelligence and sentiment analysis.

[0838] Terminal: Responsible for sending user requests and displaying generated content.

[0839] Generative artificial intelligence models: These include OpenAI and Google's AI models, used to automatically generate training modules for improving the skills of sales staff.

[0840] Emotion analysis engine: Uses technologies to analyze user emotions, such as Microsoft Azure's Emotion API and Google Cloud's Vision API.

[0841] Dialogue generation artificial intelligence models: Natural language processing models such as GPT-3 and BERT are used to automatically generate customer response dialogue tailored to the user's situation.

[0842] System Operation Overview

[0843] The user logs into the system and submits a request for a training module to improve their skills. The terminal sends this request to the server in JSON format. The server receives and parses the request and invokes an emotion analysis engine to recognize the user's emotions. After the emotion analysis engine analyzes the user's emotional state, the server invokes a generative artificial intelligence model based on that information and generates an appropriate training module. This training module is customized according to the user's emotional state (e.g., if the user is feeling stressed, it will include relaxation techniques). The generated training module is then provided to the user via the terminal.

[0844] For example, consider a case where a new sales staff member requests a training module to improve their communication skills. When the user enters information into a form and clicks the submit button, the device generates JSON data in the following format:

[0845] json

[0846] {

[0847] "userId": "A12345",

[0848] "name": "Mr. A",

[0849] "skillRequest": "Communication skills"

[0850] }

[0851] The server receives this request and uses its emotion analysis engine to analyze whether the user is experiencing stress. It then calls a generative AI model to generate a training module like the following:

[0852] json

[0853] {

[0854] "module": "Communication Basics",

[0855] "exercises": ["Conversation simulation", "Listening practice"]

[0856] "addedModule": "Relaxation Techniques"

[0857] }

[0858] This information is sent back to the device and provided to the user.

[0859] Furthermore, if a user requests customer service dialogue in a specific situation, the process follows a similar flow. For example, if a user requests a "greeting message for a new customer," the device sends a request to the server as follows:

[0860] json

[0861] {

[0862] "userId": "A12345",

[0863] "name": "Mr. A",

[0864] "situation": "Greetings to new customers"

[0865] }

[0866] The server uses an emotion analysis engine to analyze the user's emotional state and invokes a speech generation AI model to generate the following speech:

[0867] json

[0868] {

[0869] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[0870] }

[0871] This message is sent back to the device and displayed to the user.

[0872] Example of a prompt

[0873] The following is an example of a prompt message sent to an AI model:

[0874] For training modules:

[0875] "New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing."

[0876] In the case of customer service conversations:

[0877] "New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message."

[0878] As described above, this system improves the skills and productivity of sales staff. Furthermore, by enabling flexible responses tailored to the user's emotional state, it contributes to increased customer satisfaction.

[0879] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0880] Step 1:

[0881] The user enters and submits a skill content request.

[0882] Input: The user logs into the system and enters request information for skill improvement (e.g., name, ID, skill area) into the UI input form.

[0883] Specific action: The user enters information and clicks the "Submit" button.

[0884] Output: The terminal converts the input information into JSON format and generates request data like this:

[0885] json

[0886] {

[0887] "userId": "A12345",

[0888] "name": "Mr. A",

[0889] "skillRequest": "Communication skills"

[0890] }

[0891] Step 2:

[0892] The terminal sends a request to the server.

[0893] Input: Request data in JSON format containing information entered by the user.

[0894] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[0895] Output: Request data in JSON format is sent to the server.

[0896] Step 3:

[0897] The server receives the request and parses the data.

[0898] Input: Request data in JSON format sent from the terminal.

[0899] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and skill request information.

[0900] Output: Analyzed user information is obtained.

[0901] Step 4:

[0902] The server invokes an emotion analysis engine to analyze the user's emotions.

[0903] Input: Analyzed user information.

[0904] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[0905] Output: The user's emotional state (e.g., stress, tension) is obtained.

[0906] Step 5:

[0907] The server invokes a generative artificial intelligence model and generates training content.

[0908] Input: User information and sentiment analysis results.

[0909] Specific operation: The server sends this information to the generative artificial intelligence model in the form of prompt statements. For example, the following prompt statements are used:

[0910] text

[0911] New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing.

[0912] Output: A customized training module is obtained from the generative artificial intelligence model. Example:

[0913] json

[0914] {

[0915] "module": "Communication Basics",

[0916] "exercises": ["Conversation simulation", "Listening practice"]

[0917] "addedModule": "Relaxation Techniques"

[0918] }

[0919] Step 6:

[0920] The server sends the generated training module to the terminal.

[0921] Input: The generated training module.

[0922] Specific operation: The server returns the training module to the terminal as a JSON response.

[0923] Output: JSON-formatted response data received by the terminal.

[0924] Step 7:

[0925] The device provides the user with a training module.

[0926] Input: Training module received from the server.

[0927] Specific operation: The device analyzes this data and presents it to the user visually. The screen displays a "Start" button and training content.

[0928] Output: An environment is created where users can visually check and run training modules.

[0929] Step 8:

[0930] The user enters and submits a customer support chat request.

[0931] Input: Request information for customer service dialogue in a specific situation (e.g., situation, staff name).

[0932] Specific action: The user enters information and clicks the "Submit" button.

[0933] Output: The terminal converts the input information into JSON format and generates request data like this:

[0934] json

[0935] {

[0936] "userId": "A12345",

[0937] "name": "Mr. A",

[0938] "situation": "Greetings to new customers"

[0939] }

[0940] Step 9:

[0941] The terminal sends a request to the server.

[0942] Input: Request data in JSON format containing information entered by the user.

[0943] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[0944] Output: Request data in JSON format is sent to the server.

[0945] Step 10:

[0946] The server receives the request and parses the data.

[0947] Input: Request data in JSON format sent from the terminal.

[0948] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and status information.

[0949] Output: Analyzed situation and staff information are obtained.

[0950] Step 11:

[0951] The server invokes an emotion analysis engine to analyze the user's emotions.

[0952] Input: Analyzed situation and staff information.

[0953] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[0954] Output: The user's emotional state (e.g., tension) is obtained.

[0955] Step 12:

[0956] The server invokes an artificial intelligence mechanism for generating conversational responses, which then generates appropriate customer service dialogue.

[0957] Input: Situation information and emotion analysis results.

[0958] Specific operation: The server sends this information to the AI ​​talk generation model in the form of prompt statements. For example, the following prompt statements are used:

[0959] text

[0960] New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message.

[0961] Output: Customized customer service dialogue is obtained from the AI ​​talk generation model. Example:

[0962] json

[0963] {

[0964] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[0965] }

[0966] Step 13:

[0967] The server sends the generated customer interaction message to the terminal.

[0968] Input: Generated customer interaction chat.

[0969] Specific operation: The server sends the customer interaction conversation back to the terminal as a JSON response.

[0970] Output: JSON-formatted response data received by the terminal.

[0971] Step 14:

[0972] The terminal provides the user with customer service dialogue.

[0973] Input: Customer interaction messages received from the server.

[0974] Specific operation: The device analyzes this data and presents it to the user visually. The generated chat content is displayed on the screen.

[0975] Output: An environment is created where users can visually review customer interaction scripts and use them in actual customer interactions.

[0976] (Application Example 2)

[0977] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0978] Sales staff's customer service varies depending on their individual skills and emotional states, making it difficult to achieve consistently high-quality service. Furthermore, training and follow-up tailored to each sales staff member's emotional state may be insufficient. Therefore, there is a need for skill standardization and increased productivity.

[0979] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generative artificial intelligence means for generating training modules based on sales staff information, an information processing device for providing the generated training modules to the sales staff, a talk generation artificial intelligence means for generating customer service talk according to the sales staff's information and situation, an information processing device for providing the generated customer service talk to the sales staff, an emotion recognition means for recognizing the emotional state of the sales staff, and an emotion adjustment means for adjusting the training modules and customer service talk based on information obtained from the emotion recognition means. This enables flexible responses and skill standardization according to the emotional state of the sales staff.

[0980] "Sales staff" are store employees whose primary role is to introduce and sell products and services to customers.

[0981] "Skill standardization" means ensuring that all sales staff have the same level of knowledge and ability.

[0982] "Productivity improvement" refers to increasing the efficiency of operations so that more results can be achieved with fewer resources.

[0983] A "system" is a collection of devices and methods designed to improve the skills of sales staff and enhance the quality of customer service.

[0984] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules based on information from sales staff.

[0985] An "information processing device" is a device or system that analyzes collected data and provides sales staff with the information and skill content they need.

[0986] "AI-generated dialogue means" refers to artificial intelligence technology that automatically generates appropriate customer service dialogue based on the information and situation of sales staff.

[0987] "Emotion recognition means" refers to technology that analyzes the facial expressions and voice of sales staff to recognize their emotional state.

[0988] "Emotional adjustment techniques" are technologies for appropriately adjusting training modules and customer service dialogues based on the recognized emotional state of sales staff.

[0989] "Users" refer to sales staff who actually use this system to acquire training modules and customer service scripts.

[0990] A "terminal" is a device (such as smart glasses, smartphones, or head-mounted displays) that a user uses to access the system and obtain training modules and customer service dialogues.

[0991] A "server" is a computer system that manages the entire system, including generative artificial intelligence means and talk generation artificial intelligence means, and performs the necessary data processing.

[0992] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff, and furthermore, it recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. Specifically, it is realized through the following configuration and processing procedure.

[0993] System Overview

[0994] The system of the present invention includes the following main hardware and software.

[0995] Hardware:

[0996] Smart glasses (with camera and display)

[0997] Servers (cloud servers and local servers)

[0998] software:

[0999] Python

[1000] OpenCV (image processing library)

[1001] Requests (HTTP Request Library)

[1002] Program processing

[1003] emotion recognition

[1004] The system uses the camera on smart glasses attached to the device to acquire a facial image of the user (sales staff). The acquired facial image is analyzed using the OpenCV image processing library, and the user's emotional state is determined by emotion recognition. Emotional states include, for example, "tension," "stress," and "reassurance."

[1005] Training module generation

[1006] Based on emotion recognition results and information about the sales staff, a generative artificial intelligence (AI) system on the server generates appropriate training modules. This AI system creates training content considering the sales staff's communication skills, product knowledge, and problem-solving abilities. Depending on the emotional state, training modules including, for example, relaxation techniques are generated.

[1007] Generating customer service dialogues

[1008] To address specific situations requested by users, an AI-powered dialogue generation system on the server generates customer service dialogue based on emotion recognition results and sales staff information. This system creates appropriate greetings and product descriptions according to the sales staff's name and situation information. If the emotional state is tense, a concise and reassuring dialogue is provided.

[1009] Information provision

[1010] The generated training modules and customer service dialogues are provided to the user via a terminal. They are displayed on the smart glasses' screen and can be used by the user in real time.

[1011] Specific example

[1012] For example, consider a scenario where a new sales staff member uses the system. Imagine the sales staff member wearing smart glasses and greeting a new customer. If the server detects that the sales staff member is nervous, it will provide a generated conversation based on prompts such as the following:

[1013] Example of a prompt:

[1014] Based on "Person A's nervous feelings," generate a "greeting speech for a new customer." Provide a simple greeting that will put the customer at ease.

[1015] The smart glasses display a concise and reassuring message such as, "Hello, what are you looking for today?" This enables sales staff to provide consistent, high-quality service, improving customer satisfaction.

[1016] The system of this invention allows sales staff to receive appropriate training and customer support in real time, tailored to their own emotional state, resulting in standardized skills and improved productivity.

[1017] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1018] Step 1:

[1019] The user puts on the smart glasses and presses the start button. The smart glasses' camera acquires a facial image. The facial image is captured in real time and sent to the terminal. The input is the user's facial image, and the output is the transmission of the facial image to the terminal. This process involves enabling the camera function, capturing a facial image, and sending it.

[1020] Step 2:

[1021] The device analyzes facial images acquired from the camera using OpenCV and extracts facial feature points. Next, it performs emotion recognition based on these feature points. The input is the acquired facial image, and the output is the recognized emotional state (e.g., "stressed"). This process uses image processing and a machine learning model for emotion recognition.

[1022] Step 3:

[1023] The device sends the recognized emotional state and basic user information (ID and name) to the server in JSON format. The input is the emotional state and user information, and the output is the transmission of JSON data to the server. This process involves data format conversion and sending an HTTP request.

[1024] Step 4:

[1025] The server parses the received JSON data to obtain the user's emotional state and basic information. Based on the parsed data, it invokes a generative artificial intelligence system to generate an appropriate training module. The input is the received JSON data, and the output is the generated training module. This process involves data analysis and invoking an AI model.

[1026] Step 5:

[1027] The server uses a separate AI-powered talk generation mechanism to generate customer service dialogue based on the user's emotional state and basic information. The input consists of user information, situation information, and emotional state, while the output is the generated customer service dialogue. This process involves data analysis and AI model calls.

[1028] Step 6:

[1029] The server returns the generated training module and customer interaction dialogue to the terminal in JSON format. The input is the generated training module and customer interaction dialogue, and the output is the JSON response to the terminal. This process involves data format conversion and sending of an HTTP response.

[1030] Step 7:

[1031] The terminal analyzes the training module and customer interaction dialogue received from the server and displays them on the smart glasses' display. The input is JSON data from the server, and the output is the training module and customer interaction dialogue displayed on the screen. This process involves data analysis and display operations.

[1032] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1033] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1034] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1035] [Third Embodiment]

[1036] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1037] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1038] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1039] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1040] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1041] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1042] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1043] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1044] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1045] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1046] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1047] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1048] This invention is a system aimed at standardizing the skills of sales staff and improving productivity. This system is implemented as follows.

[1049] Skill content creation and delivery

[1050] 1. User requests for skill content

[1051] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1052] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1053] 2. Server receiving and processing requests

[1054] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1055] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1056] 3. Provision of generated skill content

[1057] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[1058] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1059] Generating and providing customer service dialogues

[1060] 1. Customer talk requests from users

[1061] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1062] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1063] 2. Server receiving and processing requests

[1064] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1065] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[1066] 3. Provision of generated customer interaction scripts.

[1067] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[1068] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1069] Specific example

[1070] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and generates a training module based on A's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to A via the terminal.

[1071] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI to generate specific greetings and product descriptions. The generated talks are then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[1072] As a result, the present invention can improve the skills of sales staff and standardize the quality of customer service, thereby significantly improving sales efficiency.

[1073] The following describes the processing flow.

[1074] Skill content creation and delivery

[1075] Step 1:

[1076] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1077] Step 2:

[1078] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1079] Step 3:

[1080] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1081] Step 4:

[1082] The server invokes a generative artificial intelligence (AI) system based on staff information. The AI ​​system analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1083] Step 5:

[1084] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1085] Step 6:

[1086] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1087] Generating and providing customer service dialogues

[1088] Step 1:

[1089] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1090] Step 2:

[1091] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1092] Step 3:

[1093] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1094] Step 4:

[1095] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The talk generation AI mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1096] Step 5:

[1097] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1098] Step 6:

[1099] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1100] (Example 1)

[1101] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1102] Standardizing the skills and improving the productivity of sales staff are important challenges for many companies. In particular, since sales staff skills depend on individual experience and knowledge, standardizing them is difficult. Furthermore, providing high-quality customer service tailored to each situation is also not easy. Therefore, there has been a need for efficient and effective means to standardize the skills of sales staff and improve productivity.

[1103] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1104] In this invention, the server includes terminal means for receiving requests from users, converting information into JSON format and sending it to the server; generative artificial intelligence means for analyzing the JSON data sent to the server, calling a generation AI model based on the analysis results and generating an appropriate training module; means for sending and displaying the generated training module again as a JSON response to the terminal; means for receiving customer service talk requests from users, analyzing data including situation and staff information, calling a talk generation artificial intelligence based on the analysis results; and means for sending and displaying the customer service talk generated by the talk generation artificial intelligence as a JSON response to the terminal. This enables the standardization of sales staff skills and high-quality customer service tailored to the situation.

[1105] A "terminal device" is a device that has the function of receiving requests from users, converting the information into JSON format, and sending it to the server.

[1106] A "generative artificial intelligence means" is a system that includes artificial intelligence that analyzes JSON data sent to a server and generates appropriate training modules based on the analysis results.

[1107] A "generative AI model" is a general term for artificial intelligence algorithms that generate training modules and customer service dialogues based on the skills and abilities of sales staff.

[1108] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a standard for organizing data into a data structure that is easy for both humans and machines to read.

[1109] A "talk generation artificial intelligence means" is a system that includes artificial intelligence that analyzes user request data and generates appropriate customer response talk based on the situation and staff information.

[1110] A "prompt sentence" is an input sentence given to a generative AI model to enable it to perform predictions or generation.

[1111] "Response" is a term that refers to the response data sent from a server to a terminal.

[1112] A "training module" is a collection of learning programs and materials designed to improve the skills of sales staff.

[1113] "Customer service dialogue" refers to phrases and explanations used for customer service in specific situations.

[1114] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system utilizes generative artificial intelligence means and talk generation artificial intelligence means to improve the skills of sales staff and the quality of customer service.

[1115] Skill content creation and delivery

[1116] First, users request training modules through the system's UI (user interface) to improve their skills. When a user enters the necessary information (ID, name, etc.) into the request form and clicks the submit button, the device converts this input data into JSON format and sends it to the server.

[1117] The server receives POST requests at a specific endpoint and parses the received data in JSON format. Next, it extracts user information (ID, name, etc.) from the parsed data and uses this to send a prompt to a generative artificial intelligence (e.g., the GPT-4 API). The generative AI generates a training module and returns a response to the server.

[1118] The server compiles the generated training modules into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then view the displayed training modules and work to improve their skills.

[1119] Generating and providing customer service dialogues

[1120] Next, the user makes a request via the UI to retrieve a conversation appropriate for a specific customer interaction situation. The user enters the situation (e.g., new customer interaction, product explanation) and their own information, and clicks the submit button, at which point the device sends this data to the server in JSON format.

[1121] The server receives POST requests at a specific endpoint and parses the data in JSON format. It extracts situation and staff information from the parsed data and uses this to send prompt messages to a talk generation artificial intelligence (e.g., GPT-4 API). The talk generation artificial intelligence generates appropriate customer service dialogue and returns a response to the server.

[1122] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then interact with the customer based on the displayed conversation.

[1123] Specific example

[1124] For example, consider the process by which a new sales staff member obtains their training module. This sales staff member logs into the system, enters their ID and name into the request form, and then clicks the submit button. The terminal converts this information into JSON format and sends it to the server. The server receives and analyzes this data, then calls a generative artificial intelligence (GPT-4) to generate a training module. The generated module is sent to the terminal as a JSON response and displayed.

[1125] Furthermore, when a new sales staff member interacts with a new customer in the store, they can request appropriate customer service dialogue. Once the staff member inputs the situation and submits the request, the terminal converts the data into JSON format and sends it to the server. The server receives and analyzes the data, invokes the dialogue generation artificial intelligence (GPT-4), and generates appropriate dialogue. The generated dialogue is then sent to the terminal as a JSON response and displayed.

[1126] Example of a prompt

[1127] An example of a prompt message in a skill content request is as follows:

[1128] "Generate training modules to improve product knowledge and problem-solving skills based on user IDs and names."

[1129] An example of a prompt in a customer talk request is as follows:

[1130] "Please generate a greeting message for new customers based on their user ID and name."

[1131] The above describes specific embodiments for carrying out the present invention. This system effectively enables the standardization of sales staff skills and improvement of productivity.

[1132] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1133] Skill content creation and delivery

[1134] Step 1:

[1135] The user makes a request

[1136] The user logs into the application to obtain the training module and enters the required information (ID, name, etc.) into the request form. The user then clicks the submit button on the form.

[1137] Input: User ID, name, and other information

[1138] Output: Event when the submit button was clicked

[1139] Step 2:

[1140] The device sends the request to the server.

[1141] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[1142] Input: User ID, name, and other information

[1143] Output: JSON data, HTTP POST request

[1144] Step 3:

[1145] The server receives the request.

[1146] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[1147] Input: JSON data, HTTP POST request

[1148] Output: Parsed user ID, name, and other information

[1149] Step 4:

[1150] The server invokes a generative artificial intelligence.

[1151] The server sends a prompt message to a generative artificial intelligence (e.g., GPT-4) based on the extracted user information. The generative artificial intelligence then generates an appropriate training module based on the information received.

[1152] Input: User ID, name, and other information

[1153] Output: The generated training module (e.g., a training module on product knowledge)

[1154] Step 5:

[1155] The server sends a response to the terminal.

[1156] The server compiles the generated training modules into a JSON response and sends it back to the terminal as an HTTP response.

[1157] Input: Generated training module (in JSON format)

[1158] Output: HTTP response, data in JSON format

[1159] Step 6:

[1160] The device displays skill content.

[1161] The terminal receives a response from the server and parses its contents. It then displays the parsed training module in the user interface (UI).

[1162] Users can view the displayed skill content and begin training.

[1163] Input: JSON data, HTTP response

[1164] Output: Training modules displayed in the user interface

[1165] Generating and providing customer service dialogues

[1166] Step 1:

[1167] The user makes a request

[1168] The user fills out a request form in the application to obtain a conversation appropriate for a specific situation. For example, they enter the situation (e.g., new customer support, product explanation) and their own information. The user then clicks the submit button on the form.

[1169] Input: Situation, User information

[1170] Output: Event when the submit button was clicked

[1171] Step 2:

[1172] The device sends the request to the server.

[1173] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[1174] Input: Situation, User information

[1175] Output: JSON data, HTTP POST request

[1176] Step 3:

[1177] The server receives the request.

[1178] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[1179] Input: JSON data, HTTP POST request

[1180] Output: Parsed situation, user information

[1181] Step 4:

[1182] The server invokes the AI ​​for generating speech.

[1183] The server sends a prompt message to the AI ​​that generates the conversation (e.g., GPT-4) based on the extracted situation and user information. The AI ​​generates an appropriate customer response conversation based on the information sent.

[1184] Input: Situation, User information

[1185] Output: Generated customer interaction dialogue (e.g., greeting, product description)

[1186] Step 5:

[1187] The server sends a response to the terminal.

[1188] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal as an HTTP response.

[1189] Input: Generated customer interaction chat (JSON format)

[1190] Output: HTTP response, data in JSON format

[1191] Step 6:

[1192] The device displays customer support chat.

[1193] The terminal receives a response from the server and parses its contents. The parsed customer interaction conversation is then displayed in the user interface (UI). The user can then interact with the customer based on the displayed conversation.

[1194] Input: JSON data, HTTP response

[1195] Output: Customer interaction talk displayed in the user interface

[1196] The above outlines the processing flow of this system's program. Through the specific actions performed at each processing step, users can efficiently acquire training modules for skill improvement and customer service dialogue appropriate to different situations.

[1197] (Application Example 1)

[1198] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1199] Sales staff have varying skill levels, which can lead to inconsistent customer service quality and negatively impact customer satisfaction and sales efficiency. This problem is particularly pronounced among new and less experienced staff, requiring individual skill development and training to achieve consistent, high-quality customer service. Furthermore, efficient customer service necessitates a system that provides quick and appropriate responses. In addition, there is a growing need for user-friendly systems in busy shop environments.

[1200] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1201] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing device for providing the generated training modules to sales staff; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of sales staff; and an application that is installed on a smartphone or wearable device and can be easily used by sales staff on the shop floor. This ensures that the skills of sales staff are standardized reliably and quickly, enabling high-quality customer service.

[1202] "Sales staff" refers to employees who provide products and services to customers in stores or sales environments.

[1203] "Skill standardization" refers to the process of reducing the differences in skills and knowledge among multiple sales staff so that everyone can perform their duties at a consistently high level.

[1204] "Productivity improvement" refers to improving the work efficiency and output of sales staff. Specifically, it means improving the ratio of labor input to results obtained in sales operations.

[1205] "Generative artificial intelligence means" refers to artificial intelligence technology used to generate appropriate training modules based on information from sales staff.

[1206] "Information processing device" refers to a device or system for providing generated training modules and customer service scripts to sales staff.

[1207] "AI-generated dialogue means" refers to artificial intelligence technology that generates the necessary dialogue (greetings, product descriptions, responses to questions, etc.) for customer service based on the information and situation of the sales staff.

[1208] A "smartphone" refers to a multi-functional device that combines the capabilities of a mobile phone and a computer, and can run a variety of applications.

[1209] A "wearable device" refers to a computer device that can be worn by the user. Examples include smart glasses and smartwatches.

[1210] An "application" refers to a software program that provides specific functions or services. It is installed on smartphones and wearable devices and performs various operations and provides information.

[1211] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system is operated via an application installed on a smartphone or wearable device. Specific embodiments of this system will be described in detail below.

[1212] Skill content creation and delivery

[1213] 1. User requests for skill content

[1214] Users (sales staff) make requests to retrieve their own skill content through the application's UI (user interface).

[1215] The device (smartphone or wearable device) sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1216] 2. Server receiving and processing requests

[1217] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1218] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1219] 3. Provision of generated skill content

[1220] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[1221] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1222] Generating and providing customer service dialogues

[1223] 1. Customer talk requests from users

[1224] Users (sales staff) make requests through the application's UI to obtain conversational phrases appropriate for specific situations. Examples include greeting new customers or responding to product inquiries.

[1225] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1226] 2. Server receiving and processing requests

[1227] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1228] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[1229] 3. Provision of generated customer interaction scripts.

[1230] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[1231] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1232] Specific example

[1233] For example, consider a scenario where a new sales staff member uses the system. The staff member logs into the system to obtain their training module and requests it. The terminal sends the staff member's information to the server. The server invokes generative artificial intelligence and generates a training module based on the staff member's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to the staff member via the terminal.

[1234] Furthermore, when staff members interact with new customers in stores, they can request appropriate greetings and product descriptions. The terminal sends the situation and the staff member's name to the server. The server invokes AI for dialogue generation to create specific greetings and product descriptions. The generated dialogue is then provided to the staff member via the terminal. As a result, staff members can provide consistent, high-quality service, leading to improved customer satisfaction.

[1235] Example of a prompt

[1236] For example, here's a specific example of what to do if a new customer says, "This is my first time visiting this store":

[1237] Prompt message:

[1238] Staff name: Taro Yamada

[1239] Situation: A first-time customer has visited the store. Please generate an appropriate greeting for them.

[1240] As a result, this invention improves the skills of sales staff and standardizes the quality of customer service, thereby significantly improving sales efficiency.

[1241] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1242] Step 1:

[1243] The user (sales staff) interacts with the application's UI to make a request to retrieve their skill content. This request includes basic information such as the user's ID and name. This information is stored on the device as JSON data and later sent to the server.

[1244] Step 2:

[1245] The terminal sends the user-entered request data as a POST request to a specific endpoint on the server. The input data includes the sales staff's ID and name, and is encoded in JSON format. The terminal then waits for a response from the server.

[1246] Step 3:

[1247] The server parses the received POST request to obtain information about the sales staff. This parsing process involves parsing data in JSON format. The user information obtained as a result of the parsing is then passed to a generative artificial intelligence system within the server.

[1248] Step 4:

[1249] The server invokes generative artificial intelligence (AI) means to generate appropriate training modules based on staff information. Specifically, it evaluates staff communication skills, product knowledge, problem-solving abilities, etc., and constructs training content suitable for these skills. A generative AI model is used in this process.

[1250] Step 5:

[1251] The generated training content is encoded in JSON format and sent from the server to the terminal as a response. The terminal receives this response and expands the data on the application for display to the user. This allows the user to utilize specific training modules to strengthen their weaknesses.

[1252] Step 6:

[1253] The user then uses the application to request appropriate conversation during customer service at the store. This request data includes basic information such as the customer's situation and the user's name. This information is also prepared to be sent to the terminal in JSON format.

[1254] Step 7:

[1255] The terminal sends customer talk request data to the server. The sent data arrives at a specific endpoint on the server as a POST request. The terminal waits for the server's response and, based on the generated appropriate talk, displays it to the user.

[1256] Step 8:

[1257] The server analyzes the customer talk request and invokes an AI talk generation tool to generate customer interaction dialogue. This process creates specific dialogue based on the sales staff member's name and the situation. For example, it generates a response for the situation, "This is my first time visiting this store." An example prompt might be: "Staff name: Taro Yamada\nSituation: A first-time customer has visited the store. Please generate appropriate greeting dialogue for them."

[1258] Step 9:

[1259] The generated customer interaction chat is sent back from the server to the terminal in JSON format. The terminal receives this response and displays it to the user through the application. By using this generated chat during customer interactions, users can provide consistent, high-quality service.

[1260] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1261] This invention aims to standardize the skills and improve the productivity of sales staff, and further, it is a system that recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. This system is implemented as follows.

[1262] Skill content creation and delivery

[1263] 1. User requests for skill content

[1264] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1265] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1266] 2. Server receiving and processing requests

[1267] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1268] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1269] 3. Generation of training content using generative artificial intelligence methods

[1270] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[1271] The generated training modules are tailored to the user's emotions. For example, if the user is feeling stressed, a training module including relaxation techniques will be generated.

[1272] 4. Provision of generated skill content

[1273] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1274] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1275] Generating and providing customer service dialogues

[1276] 1. Customer talk requests from users

[1277] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1278] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1279] 2. Server receiving and processing requests

[1280] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1281] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1282] 3. Dialogue generation using AI-powered dialogue generation tools

[1283] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1284] The generated customer service messages are tailored based on perceived emotions. For example, if a user is feeling anxious, a concise and reassuring message will be generated.

[1285] 4. Providing generated customer interaction scripts.

[1286] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1287] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1288] Specific example

[1289] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and an emotion engine to generate a training module that takes A's emotions into account, based on A's communication skills, product knowledge, and problem-solving abilities. For example, if A is feeling stressed, a module including relaxation techniques will be provided. The generated training module is then delivered to A via the terminal.

[1290] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI and an emotion engine to generate specific greetings and product descriptions tailored to Person A's emotional state. For example, if Person A is nervous, a concise and reassuring message is generated. The generated message is then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[1291] This invention enables improved sales staff skills and standardized customer service quality, thereby increasing productivity. Furthermore, the introduction of an emotion engine allows for flexible responses tailored to the emotional state of staff, leading to further improvements in operational efficiency.

[1292] The following describes the processing flow.

[1293] Skill content creation and delivery

[1294] Step 1:

[1295] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1296] Step 2:

[1297] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1298] Step 3:

[1299] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1300] Step 4:

[1301] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1302] Step 5:

[1303] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[1304] Step 6:

[1305] The server adjusts the generated training modules based on the user's emotions. For example, if the user is feeling stressed, a training module that includes relaxation techniques will be generated.

[1306] Step 7:

[1307] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1308] Step 8:

[1309] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1310] Generating and providing customer service dialogues

[1311] Step 1:

[1312] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1313] Step 2:

[1314] The terminal sends this request to the server in JSON format. The request data includes situation and staff information.

[1315] Step 3:

[1316] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1317] Step 4:

[1318] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1319] Step 5:

[1320] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1321] Step 6:

[1322] The server adjusts the generated customer interaction dialogue based on the user's emotions. For example, if the user is feeling anxious, a concise and reassuring dialogue will be generated.

[1323] Step 7:

[1324] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1325] Step 8:

[1326] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1327] (Example 2)

[1328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1329] Traditional sales staff training systems struggled to provide appropriate training modules and customer service phrases tailored to staff skills and specific situations. Furthermore, training and interactions that disregarded staff emotional states led to decreased productivity and difficulty in improving customer satisfaction. A system was needed to address these challenges, standardize sales staff skills, improve productivity, and enhance customer satisfaction.

[1330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1331] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing means for providing the generated training modules to the sales staff; an emotion analysis means for recognizing the emotions of the sales staff and adjusting the training modules; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of the sales staff; and an information processing means for providing the generated customer service talk to the sales staff. This enables sales staff to perform appropriate training and customer service tailored to their own emotional state.

[1332] "Sales staff" is a general term for employees who are responsible for selling products.

[1333] "Skill standardization" is the process of reducing differences in staff abilities and skills in specific tasks and bringing them to a uniform level.

[1334] "Productivity improvement" is a process that aims to produce more results or deliverables with a given amount of resources and time.

[1335] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules and content based on specific data and information.

[1336] "Information processing device" is a general term for computer systems that have the ability to receive, analyze, convert, and transmit data.

[1337] "Emotional analysis methods" refer to technologies that analyze a user's emotional state through their facial expressions, voice tone, input speed, and other factors.

[1338] "Conversation generation artificial intelligence means" refers to artificial intelligence technology that automatically generates conversations and texts based on specific conditions and information.

[1339] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system recognizes the emotions of sales staff and generates and provides training modules and customer service dialogues based on those emotions, thereby improving staff skills and the quality of customer service.

[1340] Hardware and software to be used

[1341] This system uses the following hardware and software:

[1342] Server: Responsible for receiving requests, analyzing data, and executing generative artificial intelligence and sentiment analysis.

[1343] Terminal: Responsible for sending user requests and displaying generated content.

[1344] Generative artificial intelligence models: These include OpenAI and Google's AI models, used to automatically generate training modules for improving the skills of sales staff.

[1345] Emotion analysis engine: Uses technologies to analyze user emotions, such as Microsoft Azure's Emotion API and Google Cloud's Vision API.

[1346] Dialogue generation artificial intelligence models: Natural language processing models such as GPT-3 and BERT are used to automatically generate customer response dialogue tailored to the user's situation.

[1347] System Operation Overview

[1348] The user logs into the system and submits a request for a training module to improve their skills. The terminal sends this request to the server in JSON format. The server receives and parses the request and invokes an emotion analysis engine to recognize the user's emotions. After the emotion analysis engine analyzes the user's emotional state, the server invokes a generative artificial intelligence model based on that information and generates an appropriate training module. This training module is customized according to the user's emotional state (e.g., if the user is feeling stressed, it will include relaxation techniques). The generated training module is then provided to the user via the terminal.

[1349] For example, consider a case where a new sales staff member requests a training module to improve their communication skills. When the user enters information into a form and clicks the submit button, the device generates JSON data in the following format:

[1350] json

[1351] {

[1352] "userId": "A12345",

[1353] "name": "Mr. A",

[1354] "skillRequest": "Communication skills"

[1355] }

[1356] The server receives this request and uses its emotion analysis engine to analyze whether the user is experiencing stress. It then calls a generative AI model to generate a training module like the following:

[1357] json

[1358] {

[1359] "module": "Communication Basics",

[1360] "exercises": ["Conversation simulation", "Listening practice"]

[1361] "addedModule": "Relaxation Techniques"

[1362] }

[1363] This information is sent back to the device and provided to the user.

[1364] Furthermore, if a user requests customer service dialogue in a specific situation, the process follows a similar flow. For example, if a user requests a "greeting message for a new customer," the device sends a request to the server as follows:

[1365] json

[1366] {

[1367] "userId": "A12345",

[1368] "name": "Mr. A",

[1369] "situation": "Greetings to new customers"

[1370] }

[1371] The server uses an emotion analysis engine to analyze the user's emotional state and invokes a speech generation AI model to generate the following speech:

[1372] json

[1373] {

[1374] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[1375] }

[1376] This message is sent back to the device and displayed to the user.

[1377] Example of a prompt

[1378] The following is an example of a prompt message sent to an AI model:

[1379] For training modules:

[1380] "New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing."

[1381] In the case of customer service conversations:

[1382] "New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message."

[1383] As described above, this system improves the skills and productivity of sales staff. Furthermore, by enabling flexible responses tailored to the user's emotional state, it contributes to increased customer satisfaction.

[1384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1385] Step 1:

[1386] The user enters and submits a skill content request.

[1387] Input: The user logs into the system and enters request information for skill improvement (e.g., name, ID, skill area) into the UI input form.

[1388] Specific action: The user enters information and clicks the "Submit" button.

[1389] Output: The terminal converts the input information into JSON format and generates request data like this:

[1390] json

[1391] {

[1392] "userId": "A12345",

[1393] "name": "Mr. A",

[1394] "skillRequest": "Communication skills"

[1395] }

[1396] Step 2:

[1397] The terminal sends a request to the server.

[1398] Input: Request data in JSON format containing information entered by the user.

[1399] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[1400] Output: Request data in JSON format is sent to the server.

[1401] Step 3:

[1402] The server receives the request and parses the data.

[1403] Input: Request data in JSON format sent from the terminal.

[1404] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and skill request information.

[1405] Output: Analyzed user information is obtained.

[1406] Step 4:

[1407] The server invokes an emotion analysis engine to analyze the user's emotions.

[1408] Input: Analyzed user information.

[1409] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[1410] Output: The user's emotional state (e.g., stress, tension) is obtained.

[1411] Step 5:

[1412] The server invokes a generative artificial intelligence model and generates training content.

[1413] Input: User information and sentiment analysis results.

[1414] Specific operation: The server sends this information to the generative artificial intelligence model in the form of prompt statements. For example, the following prompt statements are used:

[1415] text

[1416] New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing.

[1417] Output: A customized training module is obtained from the generative artificial intelligence model. Example:

[1418] json

[1419] {

[1420] "module": "Communication Basics",

[1421] "exercises": ["Conversation simulation", "Listening practice"]

[1422] "addedModule": "Relaxation Techniques"

[1423] }

[1424] Step 6:

[1425] The server sends the generated training module to the terminal.

[1426] Input: The generated training module.

[1427] Specific operation: The server returns the training module to the terminal as a JSON response.

[1428] Output: JSON-formatted response data received by the terminal.

[1429] Step 7:

[1430] The device provides the user with a training module.

[1431] Input: Training module received from the server.

[1432] Specific operation: The device analyzes this data and presents it to the user visually. The screen displays a "Start" button and training content.

[1433] Output: An environment is created where users can visually check and run training modules.

[1434] Step 8:

[1435] The user enters and submits a customer support chat request.

[1436] Input: Request information for customer service dialogue in a specific situation (e.g., situation, staff name).

[1437] Specific action: The user enters information and clicks the "Submit" button.

[1438] Output: The terminal converts the input information into JSON format and generates request data like this:

[1439] json

[1440] {

[1441] "userId": "A12345",

[1442] "name": "Mr. A",

[1443] "situation": "Greetings to new customers"

[1444] }

[1445] Step 9:

[1446] The terminal sends a request to the server.

[1447] Input: Request data in JSON format containing information entered by the user.

[1448] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[1449] Output: Request data in JSON format is sent to the server.

[1450] Step 10:

[1451] The server receives the request and parses the data.

[1452] Input: Request data in JSON format sent from the terminal.

[1453] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and status information.

[1454] Output: Analyzed situation and staff information are obtained.

[1455] Step 11:

[1456] The server invokes an emotion analysis engine to analyze the user's emotions.

[1457] Input: Analyzed situation and staff information.

[1458] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[1459] Output: The user's emotional state (e.g., tension) is obtained.

[1460] Step 12:

[1461] The server invokes an artificial intelligence mechanism for generating conversational responses, which then generates appropriate customer service dialogue.

[1462] Input: Situation information and emotion analysis results.

[1463] Specific operation: The server sends this information to the AI ​​talk generation model in the form of prompt statements. For example, the following prompt statements are used:

[1464] text

[1465] New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message.

[1466] Output: Customized customer service dialogue is obtained from the AI ​​talk generation model. Example:

[1467] json

[1468] {

[1469] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[1470] }

[1471] Step 13:

[1472] The server sends the generated customer interaction message to the terminal.

[1473] Input: Generated customer interaction chat.

[1474] Specific operation: The server sends the customer interaction conversation back to the terminal as a JSON response.

[1475] Output: JSON-formatted response data received by the terminal.

[1476] Step 14:

[1477] The terminal provides the user with customer service dialogue.

[1478] Input: Customer interaction messages received from the server.

[1479] Specific operation: The device analyzes this data and presents it to the user visually. The generated chat content is displayed on the screen.

[1480] Output: An environment is created where users can visually review customer interaction scripts and use them in actual customer interactions.

[1481] (Application Example 2)

[1482] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1483] Sales staff's customer service varies depending on their individual skills and emotional states, making it difficult to achieve consistently high-quality service. Furthermore, training and follow-up tailored to each sales staff member's emotional state may be insufficient. Therefore, there is a need for skill standardization and increased productivity.

[1484] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generative artificial intelligence means for generating training modules based on sales staff information, an information processing device for providing the generated training modules to the sales staff, a talk generation artificial intelligence means for generating customer service talk according to the sales staff's information and situation, an information processing device for providing the generated customer service talk to the sales staff, an emotion recognition means for recognizing the emotional state of the sales staff, and an emotion adjustment means for adjusting the training modules and customer service talk based on information obtained from the emotion recognition means. This enables flexible responses and skill standardization according to the emotional state of the sales staff.

[1485] "Sales staff" are store employees whose primary role is to introduce and sell products and services to customers.

[1486] "Skill standardization" means ensuring that all sales staff have the same level of knowledge and ability.

[1487] "Productivity improvement" refers to increasing the efficiency of operations so that more results can be achieved with fewer resources.

[1488] A "system" is a collection of devices and methods designed to improve the skills of sales staff and enhance the quality of customer service.

[1489] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules based on information from sales staff.

[1490] An "information processing device" is a device or system that analyzes collected data and provides sales staff with the information and skill content they need.

[1491] "AI-generated dialogue means" refers to artificial intelligence technology that automatically generates appropriate customer service dialogue based on the information and situation of sales staff.

[1492] "Emotion recognition means" refers to technology that analyzes the facial expressions and voice of sales staff to recognize their emotional state.

[1493] "Emotional adjustment techniques" are technologies for appropriately adjusting training modules and customer service dialogues based on the recognized emotional state of sales staff.

[1494] "Users" refer to sales staff who actually use this system to acquire training modules and customer service scripts.

[1495] A "terminal" is a device (such as smart glasses, smartphones, or head-mounted displays) that a user uses to access the system and obtain training modules and customer service dialogues.

[1496] A "server" is a computer system that manages the entire system, including generative artificial intelligence means and talk generation artificial intelligence means, and performs the necessary data processing.

[1497] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff, and furthermore, it recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. Specifically, it is realized through the following configuration and processing procedure.

[1498] System Overview

[1499] The system of the present invention includes the following main hardware and software.

[1500] Hardware:

[1501] Smart glasses (with camera and display)

[1502] Servers (cloud servers and local servers)

[1503] software:

[1504] Python

[1505] OpenCV (image processing library)

[1506] Requests (HTTP Request Library)

[1507] Program processing

[1508] emotion recognition

[1509] The system uses the camera on smart glasses attached to the device to acquire a facial image of the user (sales staff). The acquired facial image is analyzed using the OpenCV image processing library, and the user's emotional state is determined by emotion recognition. Emotional states include, for example, "tension," "stress," and "reassurance."

[1510] Training module generation

[1511] Based on emotion recognition results and information about the sales staff, a generative artificial intelligence (AI) system on the server generates appropriate training modules. This AI system creates training content considering the sales staff's communication skills, product knowledge, and problem-solving abilities. Depending on the emotional state, training modules including, for example, relaxation techniques are generated.

[1512] Generating customer service dialogues

[1513] To address specific situations requested by users, an AI-powered dialogue generation system on the server generates customer service dialogue based on emotion recognition results and sales staff information. This system creates appropriate greetings and product descriptions according to the sales staff's name and situation information. If the emotional state is tense, a concise and reassuring dialogue is provided.

[1514] Information provision

[1515] The generated training modules and customer service dialogues are provided to the user via a terminal. They are displayed on the smart glasses' screen and can be used by the user in real time.

[1516] Specific example

[1517] For example, consider a scenario where a new sales staff member uses the system. Imagine the sales staff member wearing smart glasses and greeting a new customer. If the server detects that the sales staff member is nervous, it will provide a generated conversation based on prompts such as the following:

[1518] Example of a prompt:

[1519] Based on "Person A's nervous feelings," generate a "greeting speech for a new customer." Provide a simple greeting that will put the customer at ease.

[1520] The smart glasses display a concise and reassuring message such as, "Hello, what are you looking for today?" This enables sales staff to provide consistent, high-quality service, improving customer satisfaction.

[1521] The system of this invention allows sales staff to receive appropriate training and customer support in real time, tailored to their own emotional state, resulting in standardized skills and improved productivity.

[1522] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1523] Step 1:

[1524] The user puts on the smart glasses and presses the start button. The smart glasses' camera acquires a facial image. The facial image is captured in real time and sent to the terminal. The input is the user's facial image, and the output is the transmission of the facial image to the terminal. This process involves enabling the camera function, capturing a facial image, and sending it.

[1525] Step 2:

[1526] The device analyzes facial images acquired from the camera using OpenCV and extracts facial feature points. Next, it performs emotion recognition based on these feature points. The input is the acquired facial image, and the output is the recognized emotional state (e.g., "stressed"). This process uses image processing and a machine learning model for emotion recognition.

[1527] Step 3:

[1528] The device sends the recognized emotional state and basic user information (ID and name) to the server in JSON format. The input is the emotional state and user information, and the output is the transmission of JSON data to the server. This process involves data format conversion and sending an HTTP request.

[1529] Step 4:

[1530] The server parses the received JSON data to obtain the user's emotional state and basic information. Based on the parsed data, it invokes a generative artificial intelligence system to generate an appropriate training module. The input is the received JSON data, and the output is the generated training module. This process involves data analysis and invoking an AI model.

[1531] Step 5:

[1532] The server uses a separate AI-powered talk generation mechanism to generate customer service dialogue based on the user's emotional state and basic information. The input consists of user information, situation information, and emotional state, while the output is the generated customer service dialogue. This process involves data analysis and AI model calls.

[1533] Step 6:

[1534] The server returns the generated training module and customer interaction dialogue to the terminal in JSON format. The input is the generated training module and customer interaction dialogue, and the output is the JSON response to the terminal. This process involves data format conversion and sending of an HTTP response.

[1535] Step 7:

[1536] The terminal analyzes the training module and customer interaction dialogue received from the server and displays them on the smart glasses' display. The input is JSON data from the server, and the output is the training module and customer interaction dialogue displayed on the screen. This process involves data analysis and display operations.

[1537] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1538] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1539] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1540] [Fourth Embodiment]

[1541] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1542] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1543] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1544] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1545] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1546] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1547] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1548] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1549] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1550] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1551] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1552] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1553] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1554] This invention is a system aimed at standardizing the skills of sales staff and improving productivity. This system is implemented as follows.

[1555] Skill content creation and delivery

[1556] 1. User requests for skill content

[1557] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1558] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1559] 2. Server receiving and processing requests

[1560] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1561] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1562] 3. Provision of generated skill content

[1563] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[1564] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1565] Generating and providing customer service dialogues

[1566] 1. Customer talk requests from users

[1567] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1568] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1569] 2. Server receiving and processing requests

[1570] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1571] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[1572] 3. Provision of generated customer interaction scripts.

[1573] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[1574] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1575] Specific example

[1576] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and generates a training module based on A's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to A via the terminal.

[1577] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI to generate specific greetings and product descriptions. The generated talks are then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[1578] As a result, the present invention can improve the skills of sales staff and standardize the quality of customer service, thereby significantly improving sales efficiency.

[1579] The following describes the processing flow.

[1580] Skill content creation and delivery

[1581] Step 1:

[1582] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1583] Step 2:

[1584] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1585] Step 3:

[1586] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1587] Step 4:

[1588] The server invokes a generative artificial intelligence (AI) system based on staff information. The AI ​​system analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1589] Step 5:

[1590] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1591] Step 6:

[1592] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1593] Generating and providing customer service dialogues

[1594] Step 1:

[1595] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1596] Step 2:

[1597] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1598] Step 3:

[1599] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1600] Step 4:

[1601] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The talk generation AI mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1602] Step 5:

[1603] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1604] Step 6:

[1605] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1606] (Example 1)

[1607] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1608] Standardizing the skills and improving the productivity of sales staff are important challenges for many companies. In particular, since sales staff skills depend on individual experience and knowledge, standardizing them is difficult. Furthermore, providing high-quality customer service tailored to each situation is also not easy. Therefore, there has been a need for efficient and effective means to standardize the skills of sales staff and improve productivity.

[1609] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1610] In this invention, the server includes terminal means for receiving requests from users, converting information into JSON format and sending it to the server; generative artificial intelligence means for analyzing the JSON data sent to the server, calling a generation AI model based on the analysis results and generating an appropriate training module; means for sending and displaying the generated training module again as a JSON response to the terminal; means for receiving customer service talk requests from users, analyzing data including situation and staff information, calling a talk generation artificial intelligence based on the analysis results; and means for sending and displaying the customer service talk generated by the talk generation artificial intelligence as a JSON response to the terminal. This enables the standardization of sales staff skills and high-quality customer service tailored to the situation.

[1611] A "terminal device" is a device that has the function of receiving requests from users, converting the information into JSON format, and sending it to the server.

[1612] A "generative artificial intelligence means" is a system that includes artificial intelligence that analyzes JSON data sent to a server and generates appropriate training modules based on the analysis results.

[1613] A "generative AI model" is a general term for artificial intelligence algorithms that generate training modules and customer service dialogues based on the skills and abilities of sales staff.

[1614] "JSON format" is an abbreviation for JavaScript Object Notation, and it is a standard for organizing data into a data structure that is easy for both humans and machines to read.

[1615] A "talk generation artificial intelligence means" is a system that includes artificial intelligence that analyzes user request data and generates appropriate customer response talk based on the situation and staff information.

[1616] A "prompt sentence" is an input sentence given to a generative AI model to enable it to perform predictions or generation.

[1617] "Response" is a term that refers to the response data sent from a server to a terminal.

[1618] A "training module" is a collection of learning programs and materials designed to improve the skills of sales staff.

[1619] "Customer service dialogue" refers to phrases and explanations used for customer service in specific situations.

[1620] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system utilizes generative artificial intelligence means and talk generation artificial intelligence means to improve the skills of sales staff and the quality of customer service.

[1621] Skill content creation and delivery

[1622] First, users request training modules through the system's UI (user interface) to improve their skills. When a user enters the necessary information (ID, name, etc.) into the request form and clicks the submit button, the device converts this input data into JSON format and sends it to the server.

[1623] The server receives POST requests at a specific endpoint and parses the received data in JSON format. Next, it extracts user information (ID, name, etc.) from the parsed data and uses this to send a prompt to a generative artificial intelligence (e.g., the GPT-4 API). The generative AI generates a training module and returns a response to the server.

[1624] The server compiles the generated training modules into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then view the displayed training modules and work to improve their skills.

[1625] Generating and providing customer service dialogues

[1626] Next, the user makes a request via the UI to retrieve a conversation appropriate for a specific customer interaction situation. The user enters the situation (e.g., new customer interaction, product explanation) and their own information, and clicks the submit button, at which point the device sends this data to the server in JSON format.

[1627] The server receives POST requests at a specific endpoint and parses the data in JSON format. It extracts situation and staff information from the parsed data and uses this to send prompt messages to a talk generation artificial intelligence (e.g., GPT-4 API). The talk generation artificial intelligence generates appropriate customer service dialogue and returns a response to the server.

[1628] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal. The terminal receives this response data and displays it in the user interface. The user can then interact with the customer based on the displayed conversation.

[1629] Specific example

[1630] For example, consider the process by which a new sales staff member obtains their training module. This sales staff member logs into the system, enters their ID and name into the request form, and then clicks the submit button. The terminal converts this information into JSON format and sends it to the server. The server receives and analyzes this data, then calls a generative artificial intelligence (GPT-4) to generate a training module. The generated module is sent to the terminal as a JSON response and displayed.

[1631] Furthermore, when a new sales staff member interacts with a new customer in the store, they can request appropriate customer service dialogue. Once the staff member inputs the situation and submits the request, the terminal converts the data into JSON format and sends it to the server. The server receives and analyzes the data, invokes the dialogue generation artificial intelligence (GPT-4), and generates appropriate dialogue. The generated dialogue is then sent to the terminal as a JSON response and displayed.

[1632] Example of a prompt

[1633] An example of a prompt message in a skill content request is as follows:

[1634] "Generate training modules to improve product knowledge and problem-solving skills based on user IDs and names."

[1635] An example of a prompt in a customer talk request is as follows:

[1636] "Please generate a greeting message for new customers based on their user ID and name."

[1637] The above describes specific embodiments for carrying out the present invention. This system effectively enables the standardization of sales staff skills and improvement of productivity.

[1638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1639] Skill content creation and delivery

[1640] Step 1:

[1641] The user makes a request

[1642] The user logs into the application to obtain the training module and enters the required information (ID, name, etc.) into the request form. The user then clicks the submit button on the form.

[1643] Input: User ID, name, and other information

[1644] Output: Event when the submit button was clicked

[1645] Step 2:

[1646] The device sends the request to the server.

[1647] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[1648] Input: User ID, name, and other information

[1649] Output: JSON data, HTTP POST request

[1650] Step 3:

[1651] The server receives the request.

[1652] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[1653] Input: JSON data, HTTP POST request

[1654] Output: Parsed user ID, name, and other information

[1655] Step 4:

[1656] The server invokes a generative artificial intelligence.

[1657] The server sends a prompt message to a generative artificial intelligence (e.g., GPT-4) based on the extracted user information. The generative artificial intelligence then generates an appropriate training module based on the information received.

[1658] Input: User ID, name, and other information

[1659] Output: The generated training module (e.g., a training module on product knowledge)

[1660] Step 5:

[1661] The server sends a response to the terminal.

[1662] The server compiles the generated training modules into a JSON response and sends it back to the terminal as an HTTP response.

[1663] Input: Generated training module (in JSON format)

[1664] Output: HTTP response, data in JSON format

[1665] Step 6:

[1666] The device displays skill content.

[1667] The terminal receives a response from the server and parses its contents. It then displays the parsed training module in the user interface (UI).

[1668] Users can view the displayed skill content and begin training.

[1669] Input: JSON data, HTTP response

[1670] Output: Training modules displayed in the user interface

[1671] Generating and providing customer service dialogues

[1672] Step 1:

[1673] The user makes a request

[1674] The user fills out a request form in the application to obtain a conversation appropriate for a specific situation. For example, they enter the situation (e.g., new customer support, product explanation) and their own information. The user then clicks the submit button on the form.

[1675] Input: Situation, User information

[1676] Output: Event when the submit button was clicked

[1677] Step 2:

[1678] The device sends the request to the server.

[1679] The terminal retrieves the information entered by the user and converts it into JSON format. It then sends the converted JSON data to the server as an HTTP POST request.

[1680] Input: Situation, User information

[1681] Output: JSON data, HTTP POST request

[1682] Step 3:

[1683] The server receives the request.

[1684] The server receives POST requests at a specific HTTP endpoint. It then parses the received data into JSON format and performs analysis.

[1685] Input: JSON data, HTTP POST request

[1686] Output: Parsed situation, user information

[1687] Step 4:

[1688] The server invokes the AI ​​for generating speech.

[1689] The server sends a prompt message to the AI ​​that generates the conversation (e.g., GPT-4) based on the extracted situation and user information. The AI ​​generates an appropriate customer response conversation based on the information sent.

[1690] Input: Situation, User information

[1691] Output: Generated customer interaction dialogue (e.g., greeting, product description)

[1692] Step 5:

[1693] The server sends a response to the terminal.

[1694] The server compiles the generated customer interaction conversation into a JSON response and sends it back to the terminal as an HTTP response.

[1695] Input: Generated customer interaction chat (JSON format)

[1696] Output: HTTP response, data in JSON format

[1697] Step 6:

[1698] The device displays customer support chat.

[1699] The terminal receives a response from the server and parses its contents. The parsed customer interaction conversation is then displayed in the user interface (UI). The user can then interact with the customer based on the displayed conversation.

[1700] Input: JSON data, HTTP response

[1701] Output: Customer interaction talk displayed in the user interface

[1702] The above outlines the processing flow of this system's program. Through the specific actions performed at each processing step, users can efficiently acquire training modules for skill improvement and customer service dialogue appropriate to different situations.

[1703] (Application Example 1)

[1704] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1705] Sales staff have varying skill levels, which can lead to inconsistent customer service quality and negatively impact customer satisfaction and sales efficiency. This problem is particularly pronounced among new and less experienced staff, requiring individual skill development and training to achieve consistent, high-quality customer service. Furthermore, efficient customer service necessitates a system that provides quick and appropriate responses. In addition, there is a growing need for user-friendly systems in busy shop environments.

[1706] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1707] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing device for providing the generated training modules to sales staff; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of sales staff; and an application that is installed on a smartphone or wearable device and can be easily used by sales staff on the shop floor. This ensures that the skills of sales staff are standardized reliably and quickly, enabling high-quality customer service.

[1708] "Sales staff" refers to employees who provide products and services to customers in stores or sales environments.

[1709] "Skill standardization" refers to the process of reducing the differences in skills and knowledge among multiple sales staff so that everyone can perform their duties at a consistently high level.

[1710] "Productivity improvement" refers to improving the work efficiency and output of sales staff. Specifically, it means improving the ratio of labor input to results obtained in sales operations.

[1711] "Generative artificial intelligence means" refers to artificial intelligence technology used to generate appropriate training modules based on information from sales staff.

[1712] "Information processing device" refers to a device or system for providing generated training modules and customer service scripts to sales staff.

[1713] "AI-generated dialogue means" refers to artificial intelligence technology that generates the necessary dialogue (greetings, product descriptions, responses to questions, etc.) for customer service based on the information and situation of the sales staff.

[1714] A "smartphone" refers to a multi-functional device that combines the capabilities of a mobile phone and a computer, and can run a variety of applications.

[1715] A "wearable device" refers to a computer device that can be worn by the user. Examples include smart glasses and smartwatches.

[1716] An "application" refers to a software program that provides specific functions or services. It is installed on smartphones and wearable devices and performs various operations and provides information.

[1717] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system is operated via an application installed on a smartphone or wearable device. Specific embodiments of this system will be described in detail below.

[1718] Skill content creation and delivery

[1719] 1. User requests for skill content

[1720] Users (sales staff) make requests to retrieve their own skill content through the application's UI (user interface).

[1721] The device (smartphone or wearable device) sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1722] 2. Server receiving and processing requests

[1723] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1724] The server invokes a generative artificial intelligence (AI) system based on staff information. The generative AI analyzes basic skills such as sales staff's communication abilities, product knowledge, and problem-solving skills, and generates appropriate training modules.

[1725] 3. Provision of generated skill content

[1726] The server receives the skill content returned by the generative artificial intelligence and sends it back to the terminal as a JSON response.

[1727] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1728] Generating and providing customer service dialogues

[1729] 1. Customer talk requests from users

[1730] Users (sales staff) make requests through the application's UI to obtain conversational phrases appropriate for specific situations. Examples include greeting new customers or responding to product inquiries.

[1731] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1732] 2. Server receiving and processing requests

[1733] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1734] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation and staff information. The AI ​​generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using, for example, the name of the sales staff member.

[1735] 3. Provision of generated customer interaction scripts.

[1736] The server receives the customer interaction dialogue returned by the AI ​​that generates the dialogue and sends it back to the terminal as a JSON response.

[1737] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1738] Specific example

[1739] For example, consider a scenario where a new sales staff member uses the system. The staff member logs into the system to obtain their training module and requests it. The terminal sends the staff member's information to the server. The server invokes generative artificial intelligence and generates a training module based on the staff member's communication skills, product knowledge, and problem-solving abilities. The generated training module is then provided to the staff member via the terminal.

[1740] Furthermore, when staff members interact with new customers in stores, they can request appropriate greetings and product descriptions. The terminal sends the situation and the staff member's name to the server. The server invokes AI for dialogue generation to create specific greetings and product descriptions. The generated dialogue is then provided to the staff member via the terminal. As a result, staff members can provide consistent, high-quality service, leading to improved customer satisfaction.

[1741] Example of a prompt

[1742] For example, here's a specific example of what to do if a new customer says, "This is my first time visiting this store":

[1743] Prompt message:

[1744] Staff name: Taro Yamada

[1745] Situation: A first-time customer has visited the store. Please generate an appropriate greeting for them.

[1746] As a result, this invention improves the skills of sales staff and standardizes the quality of customer service, thereby significantly improving sales efficiency.

[1747] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1748] Step 1:

[1749] The user (sales staff) interacts with the application's UI to make a request to retrieve their skill content. This request includes basic information such as the user's ID and name. This information is stored on the device as JSON data and later sent to the server.

[1750] Step 2:

[1751] The terminal sends the user-entered request data as a POST request to a specific endpoint on the server. The input data includes the sales staff's ID and name, and is encoded in JSON format. The terminal then waits for a response from the server.

[1752] Step 3:

[1753] The server parses the received POST request to obtain information about the sales staff. This parsing process involves parsing data in JSON format. The user information obtained as a result of the parsing is then passed to a generative artificial intelligence system within the server.

[1754] Step 4:

[1755] The server invokes generative artificial intelligence (AI) means to generate appropriate training modules based on staff information. Specifically, it evaluates staff communication skills, product knowledge, problem-solving abilities, etc., and constructs training content suitable for these skills. A generative AI model is used in this process.

[1756] Step 5:

[1757] The generated training content is encoded in JSON format and sent from the server to the terminal as a response. The terminal receives this response and expands the data on the application for display to the user. This allows the user to utilize specific training modules to strengthen their weaknesses.

[1758] Step 6:

[1759] The user then uses the application to request appropriate conversation during customer service at the store. This request data includes basic information such as the customer's situation and the user's name. This information is also prepared to be sent to the terminal in JSON format.

[1760] Step 7:

[1761] The terminal sends customer talk request data to the server. The sent data arrives at a specific endpoint on the server as a POST request. The terminal waits for the server's response and, based on the generated appropriate talk, displays it to the user.

[1762] Step 8:

[1763] The server analyzes the customer talk request and invokes an AI talk generation tool to generate customer interaction dialogue. This process creates specific dialogue based on the sales staff member's name and the situation. For example, it generates a response for the situation, "This is my first time visiting this store." An example prompt might be: "Staff name: Taro Yamada\nSituation: A first-time customer has visited the store. Please generate appropriate greeting dialogue for them."

[1764] Step 9:

[1765] The generated customer interaction chat is sent back from the server to the terminal in JSON format. The terminal receives this response and displays it to the user through the application. By using this generated chat during customer interactions, users can provide consistent, high-quality service.

[1766] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1767] This invention aims to standardize the skills and improve the productivity of sales staff, and further, it is a system that recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. This system is implemented as follows.

[1768] Skill content creation and delivery

[1769] 1. User requests for skill content

[1770] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1771] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1772] 2. Server receiving and processing requests

[1773] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1774] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1775] 3. Generation of training content using generative artificial intelligence methods

[1776] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[1777] The generated training modules are tailored to the user's emotions. For example, if the user is feeling stressed, a training module including relaxation techniques will be generated.

[1778] 4. Provision of generated skill content

[1779] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1780] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1781] Generating and providing customer service dialogues

[1782] 1. Customer talk requests from users

[1783] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1784] The terminal sends this request to the server in JSON format. This request data includes status and staff information.

[1785] 2. Server receiving and processing requests

[1786] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1787] The server further analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1788] 3. Dialogue generation using AI-powered dialogue generation tools

[1789] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1790] The generated customer service messages are tailored based on perceived emotions. For example, if a user is feeling anxious, a concise and reassuring message will be generated.

[1791] 4. Providing generated customer interaction scripts.

[1792] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1793] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1794] Specific example

[1795] For example, consider a scenario where a new sales staff member, A, uses the system. A logs into the system to obtain their training module and requests it. The terminal sends A's information to the server. The server invokes generative artificial intelligence and an emotion engine to generate a training module that takes A's emotions into account, based on A's communication skills, product knowledge, and problem-solving abilities. For example, if A is feeling stressed, a module including relaxation techniques will be provided. The generated training module is then delivered to A via the terminal.

[1796] Furthermore, when Person A interacts with a new customer in a store, Person A requests appropriate greetings and product descriptions. The terminal sends the situation and Person A's name to the server. The server invokes a talk generation AI and an emotion engine to generate specific greetings and product descriptions tailored to Person A's emotional state. For example, if Person A is nervous, a concise and reassuring message is generated. The generated message is then provided to Person A via the terminal. As a result, Person A can provide consistent, high-quality service, leading to improved customer satisfaction.

[1797] This invention enables improved sales staff skills and standardized customer service quality, thereby increasing productivity. Furthermore, the introduction of an emotion engine allows for flexible responses tailored to the emotional state of staff, leading to further improvements in operational efficiency.

[1798] The following describes the processing flow.

[1799] Skill content creation and delivery

[1800] Step 1:

[1801] Users (sales staff) make requests to acquire their own skill content via the UI (user interface).

[1802] Step 2:

[1803] The device sends this request to the server as JSON data. The request data includes basic information such as the user's ID and name.

[1804] Step 3:

[1805] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves staff information.

[1806] Step 4:

[1807] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1808] Step 5:

[1809] The server invokes a generative artificial intelligence (AI) system based on staff information and recognized emotions. The AI ​​system analyzes basic skills such as the sales staff's communication skills, product knowledge, and problem-solving abilities, and generates appropriate training modules.

[1810] Step 6:

[1811] The server adjusts the generated training modules based on the user's emotions. For example, if the user is feeling stressed, a training module that includes relaxation techniques will be generated.

[1812] Step 7:

[1813] The server receives the skill content returned by the generative artificial intelligence system and returns it to the terminal as a JSON response.

[1814] Step 8:

[1815] The device receives this response and provides the user with the appropriate training module. This allows the user to receive specific training on their weaknesses and skills that need improvement.

[1816] Generating and providing customer service dialogues

[1817] Step 1:

[1818] Users (sales staff) can request appropriate conversational phrases for specific situations via the UI. Examples include greeting new customers or responding to product inquiries.

[1819] Step 2:

[1820] The terminal sends this request to the server in JSON format. The request data includes situation and staff information.

[1821] Step 3:

[1822] The server receives POST requests at a specific endpoint and parses the content as JSON. This parsing retrieves the situation and staff information.

[1823] Step 4:

[1824] The server uses an emotion engine to analyze the user's emotions. The emotion engine recognizes emotions by analyzing the user's facial expressions, voice tone, gestures, etc.

[1825] Step 5:

[1826] The server invokes a talk generation artificial intelligence (AI) mechanism based on the situation, staff information, and recognized emotions. The AI ​​mechanism generates customer service dialogue (e.g., greetings, product descriptions, and responses to questions) using the sales staff's name.

[1827] Step 6:

[1828] The server adjusts the generated customer interaction dialogue based on the user's emotions. For example, if the user is feeling anxious, a concise and reassuring dialogue will be generated.

[1829] Step 7:

[1830] The server receives the customer interaction dialogue returned by the AI-generated dialogue system and returns it to the terminal as a JSON response.

[1831] Step 8:

[1832] The terminal receives this response and displays it to the user. This allows the user to provide consistent, high-quality customer service.

[1833] (Example 2)

[1834] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1835] Traditional sales staff training systems struggled to provide appropriate training modules and customer service phrases tailored to staff skills and specific situations. Furthermore, training and interactions that disregarded staff emotional states led to decreased productivity and difficulty in improving customer satisfaction. A system was needed to address these challenges, standardize sales staff skills, improve productivity, and enhance customer satisfaction.

[1836] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1837] In this invention, the server includes a generative artificial intelligence means for generating training modules based on information about sales staff; an information processing means for providing the generated training modules to the sales staff; an emotion analysis means for recognizing the emotions of the sales staff and adjusting the training modules; a talk generation artificial intelligence means for generating customer service talk according to the information and situation of the sales staff; and an information processing means for providing the generated customer service talk to the sales staff. This enables sales staff to perform appropriate training and customer service tailored to their own emotional state.

[1838] "Sales staff" is a general term for employees who are responsible for selling products.

[1839] "Skill standardization" is the process of reducing differences in staff abilities and skills in specific tasks and bringing them to a uniform level.

[1840] "Productivity improvement" is a process that aims to produce more results or deliverables with a given amount of resources and time.

[1841] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules and content based on specific data and information.

[1842] "Information processing device" is a general term for computer systems that have the ability to receive, analyze, convert, and transmit data.

[1843] "Emotional analysis methods" refer to technologies that analyze a user's emotional state through their facial expressions, voice tone, input speed, and other factors.

[1844] "Conversation generation artificial intelligence means" refers to artificial intelligence technology that automatically generates conversations and texts based on specific conditions and information.

[1845] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff. This system recognizes the emotions of sales staff and generates and provides training modules and customer service dialogues based on those emotions, thereby improving staff skills and the quality of customer service.

[1846] Hardware and software to be used

[1847] This system uses the following hardware and software:

[1848] Server: Responsible for receiving requests, analyzing data, and executing generative artificial intelligence and sentiment analysis.

[1849] Terminal: Responsible for sending user requests and displaying generated content.

[1850] Generative artificial intelligence models: These include OpenAI and Google's AI models, used to automatically generate training modules for improving the skills of sales staff.

[1851] Emotion analysis engine: Uses technologies to analyze user emotions, such as Microsoft Azure's Emotion API and Google Cloud's Vision API.

[1852] Dialogue generation artificial intelligence models: Natural language processing models such as GPT-3 and BERT are used to automatically generate customer response dialogue tailored to the user's situation.

[1853] System Operation Overview

[1854] The user logs into the system and submits a request for a training module to improve their skills. The terminal sends this request to the server in JSON format. The server receives and parses the request and invokes an emotion analysis engine to recognize the user's emotions. After the emotion analysis engine analyzes the user's emotional state, the server invokes a generative artificial intelligence model based on that information and generates an appropriate training module. This training module is customized according to the user's emotional state (e.g., if the user is feeling stressed, it will include relaxation techniques). The generated training module is then provided to the user via the terminal.

[1855] For example, consider a case where a new sales staff member requests a training module to improve their communication skills. When the user enters information into a form and clicks the submit button, the device generates JSON data in the following format:

[1856] json

[1857] {

[1858] "userId": "A12345",

[1859] "name": "Mr. A",

[1860] "skillRequest": "Communication skills"

[1861] }

[1862] The server receives this request and uses its emotion analysis engine to analyze whether the user is experiencing stress. It then calls a generative AI model to generate a training module like the following:

[1863] json

[1864] {

[1865] "module": "Communication Basics",

[1866] "exercises": ["Conversation simulation", "Listening practice"]

[1867] "addedModule": "Relaxation Techniques"

[1868] }

[1869] This information is sent back to the device and provided to the user.

[1870] Furthermore, if a user requests customer service dialogue in a specific situation, the process follows a similar flow. For example, if a user requests a "greeting message for a new customer," the device sends a request to the server as follows:

[1871] json

[1872] {

[1873] "userId": "A12345",

[1874] "name": "Mr. A",

[1875] "situation": "Greetings to new customers"

[1876] }

[1877] The server uses an emotion analysis engine to analyze the user's emotional state and invokes a speech generation AI model to generate the following speech:

[1878] json

[1879] {

[1880] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[1881] }

[1882] This message is sent back to the device and displayed to the user.

[1883] Example of a prompt

[1884] The following is an example of a prompt message sent to an AI model:

[1885] For training modules:

[1886] "New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing."

[1887] In the case of customer service conversations:

[1888] "New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message."

[1889] As described above, this system improves the skills and productivity of sales staff. Furthermore, by enabling flexible responses tailored to the user's emotional state, it contributes to increased customer satisfaction.

[1890] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1891] Step 1:

[1892] The user enters and submits a skill content request.

[1893] Input: The user logs into the system and enters request information for skill improvement (e.g., name, ID, skill area) into the UI input form.

[1894] Specific action: The user enters information and clicks the "Submit" button.

[1895] Output: The terminal converts the input information into JSON format and generates request data like this:

[1896] json

[1897] {

[1898] "userId": "A12345",

[1899] "name": "Mr. A",

[1900] "skillRequest": "Communication skills"

[1901] }

[1902] Step 2:

[1903] The terminal sends a request to the server.

[1904] Input: Request data in JSON format containing information entered by the user.

[1905] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[1906] Output: Request data in JSON format is sent to the server.

[1907] Step 3:

[1908] The server receives the request and parses the data.

[1909] Input: Request data in JSON format sent from the terminal.

[1910] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and skill request information.

[1911] Output: Analyzed user information is obtained.

[1912] Step 4:

[1913] The server invokes an emotion analysis engine to analyze the user's emotions.

[1914] Input: Analyzed user information.

[1915] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[1916] Output: The user's emotional state (e.g., stress, tension) is obtained.

[1917] Step 5:

[1918] The server invokes a generative artificial intelligence model and generates training content.

[1919] Input: User information and sentiment analysis results.

[1920] Specific operation: The server sends this information to the generative artificial intelligence model in the form of prompt statements. For example, the following prompt statements are used:

[1921] text

[1922] New sales staff member A needs a training module. Please create an appropriate training module considering his communication skills, product knowledge, problem-solving abilities, and the stress he is currently experiencing.

[1923] Output: A customized training module is obtained from the generative artificial intelligence model. Example:

[1924] json

[1925] {

[1926] "module": "Communication Basics",

[1927] "exercises": ["Conversation simulation", "Listening practice"]

[1928] "addedModule": "Relaxation Techniques"

[1929] }

[1930] Step 6:

[1931] The server sends the generated training module to the terminal.

[1932] Input: The generated training module.

[1933] Specific operation: The server returns the training module to the terminal as a JSON response.

[1934] Output: JSON-formatted response data received by the terminal.

[1935] Step 7:

[1936] The device provides the user with a training module.

[1937] Input: Training module received from the server.

[1938] Specific operation: The device analyzes this data and presents it to the user visually. The screen displays a "Start" button and training content.

[1939] Output: An environment is created where users can visually check and run training modules.

[1940] Step 8:

[1941] The user enters and submits a customer support chat request.

[1942] Input: Request information for customer service dialogue in a specific situation (e.g., situation, staff name).

[1943] Specific action: The user enters information and clicks the "Submit" button.

[1944] Output: The terminal converts the input information into JSON format and generates request data like this:

[1945] json

[1946] {

[1947] "userId": "A12345",

[1948] "name": "Mr. A",

[1949] "situation": "Greetings to new customers"

[1950] }

[1951] Step 9:

[1952] The terminal sends a request to the server.

[1953] Input: Request data in JSON format containing information entered by the user.

[1954] Specific action: The device sends this JSON data as a POST request to the specified endpoint.

[1955] Output: Request data in JSON format is sent to the server.

[1956] Step 10:

[1957] The server receives the request and parses the data.

[1958] Input: Request data in JSON format sent from the terminal.

[1959] Specific operation: The server receives this data and parses its contents using a JSON parser. In particular, it extracts the user ID, name, and status information.

[1960] Output: Analyzed situation and staff information are obtained.

[1961] Step 11:

[1962] The server invokes an emotion analysis engine to analyze the user's emotions.

[1963] Input: Analyzed situation and staff information.

[1964] Specific operation: The server calls the sentiment analysis engine based on user identification information from the received data. The sentiment analysis engine analyzes the user's past data and real-time input data (e.g., facial expressions, voice tone) to evaluate their emotional state.

[1965] Output: The user's emotional state (e.g., tension) is obtained.

[1966] Step 12:

[1967] The server invokes an artificial intelligence mechanism for generating conversational responses, which then generates appropriate customer service dialogue.

[1968] Input: Situation information and emotion analysis results.

[1969] Specific operation: The server sends this information to the AI ​​talk generation model in the form of prompt statements. For example, the following prompt statements are used:

[1970] text

[1971] New sales staff member A needs a greeting message for new customers. He's nervous, so please create a concise and reassuring greeting message.

[1972] Output: Customized customer service dialogue is obtained from the AI ​​talk generation model. Example:

[1973] json

[1974] {

[1975] "Greeting": "Hello, I'm A. What kind of product are you looking for today?"

[1976] }

[1977] Step 13:

[1978] The server sends the generated customer interaction message to the terminal.

[1979] Input: Generated customer interaction chat.

[1980] Specific operation: The server sends the customer interaction conversation back to the terminal as a JSON response.

[1981] Output: JSON-formatted response data received by the terminal.

[1982] Step 14:

[1983] The terminal provides the user with customer service dialogue.

[1984] Input: Customer interaction messages received from the server.

[1985] Specific operation: The device analyzes this data and presents it to the user visually. The generated chat content is displayed on the screen.

[1986] Output: An environment is created where users can visually review customer interaction scripts and use them in actual customer interactions.

[1987] (Application Example 2)

[1988] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1989] Sales staff's customer service varies depending on their individual skills and emotional states, making it difficult to achieve consistently high-quality service. Furthermore, training and follow-up tailored to each sales staff member's emotional state may be insufficient. Therefore, there is a need for skill standardization and increased productivity.

[1990] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generative artificial intelligence means for generating training modules based on sales staff information, an information processing device for providing the generated training modules to the sales staff, a talk generation artificial intelligence means for generating customer service talk according to the sales staff's information and situation, an information processing device for providing the generated customer service talk to the sales staff, an emotion recognition means for recognizing the emotional state of the sales staff, and an emotion adjustment means for adjusting the training modules and customer service talk based on information obtained from the emotion recognition means. This enables flexible responses and skill standardization according to the emotional state of the sales staff.

[1991] "Sales staff" are store employees whose primary role is to introduce and sell products and services to customers.

[1992] "Skill standardization" means ensuring that all sales staff have the same level of knowledge and ability.

[1993] "Productivity improvement" refers to increasing the efficiency of operations so that more results can be achieved with fewer resources.

[1994] A "system" is a collection of devices and methods designed to improve the skills of sales staff and enhance the quality of customer service.

[1995] "Generative artificial intelligence means" refers to artificial intelligence technology that automatically generates training modules based on information from sales staff.

[1996] An "information processing device" is a device or system that analyzes collected data and provides sales staff with the information and skill content they need.

[1997] "AI-generated dialogue means" refers to artificial intelligence technology that automatically generates appropriate customer service dialogue based on the information and situation of sales staff.

[1998] "Emotion recognition means" refers to technology that analyzes the facial expressions and voice of sales staff to recognize their emotional state.

[1999] "Emotional adjustment techniques" are technologies for appropriately adjusting training modules and customer service dialogues based on the recognized emotional state of sales staff.

[2000] "Users" refer to sales staff who actually use this system to acquire training modules and customer service scripts.

[2001] A "terminal" is a device (such as smart glasses, smartphones, or head-mounted displays) that a user uses to access the system and obtain training modules and customer service dialogues.

[2002] A "server" is a computer system that manages the entire system, including generative artificial intelligence means and talk generation artificial intelligence means, and performs the necessary data processing.

[2003] This invention is a system aimed at standardizing the skills and improving the productivity of sales staff, and furthermore, it recognizes the emotions of sales staff and adjusts training modules and customer service dialogue accordingly. Specifically, it is realized through the following configuration and processing procedure.

[2004] System Overview

[2005] The system of the present invention includes the following main hardware and software.

[2006] Hardware:

[2007] Smart glasses (with camera and display)

[2008] Servers (cloud servers and local servers)

[2009] software:

[2010] Python

[2011] OpenCV (image processing library)

[2012] Requests (HTTP Request Library)

[2013] Program processing

[2014] emotion recognition

[2015] The system uses the camera on smart glasses attached to the device to acquire a facial image of the user (sales staff). The acquired facial image is analyzed using the OpenCV image processing library, and the user's emotional state is determined by emotion recognition. Emotional states include, for example, "tension," "stress," and "reassurance."

[2016] Training module generation

[2017] Based on emotion recognition results and information about the sales staff, a generative artificial intelligence (AI) system on the server generates appropriate training modules. This AI system creates training content considering the sales staff's communication skills, product knowledge, and problem-solving abilities. Depending on the emotional state, training modules including, for example, relaxation techniques are generated.

[2018] Generating customer service dialogues

[2019] To address specific situations requested by users, an AI-powered dialogue generation system on the server generates customer service dialogue based on emotion recognition results and sales staff information. This system creates appropriate greetings and product descriptions according to the sales staff's name and situation information. If the emotional state is tense, a concise and reassuring dialogue is provided.

[2020] Information provision

[2021] The generated training modules and customer service dialogues are provided to the user via a terminal. They are displayed on the smart glasses' screen and can be used by the user in real time.

[2022] Specific example

[2023] For example, consider a scenario where a new sales staff member uses the system. Imagine the sales staff member wearing smart glasses and greeting a new customer. If the server detects that the sales staff member is nervous, it will provide a generated conversation based on prompts such as the following:

[2024] Example of a prompt:

[2025] Based on "Person A's nervous feelings," generate a "greeting speech for a new customer." Provide a simple greeting that will put the customer at ease.

[2026] The smart glasses display a concise and reassuring message such as, "Hello, what are you looking for today?" This enables sales staff to provide consistent, high-quality service, improving customer satisfaction.

[2027] The system of this invention allows sales staff to receive appropriate training and customer support in real time, tailored to their own emotional state, resulting in standardized skills and improved productivity.

[2028] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2029] Step 1:

[2030] The user puts on the smart glasses and presses the start button. The smart glasses' camera acquires a facial image. The facial image is captured in real time and sent to the terminal. The input is the user's facial image, and the output is the transmission of the facial image to the terminal. This process involves enabling the camera function, capturing a facial image, and sending it.

[2031] Step 2:

[2032] The device analyzes facial images acquired from the camera using OpenCV and extracts facial feature points. Next, it performs emotion recognition based on these feature points. The input is the acquired facial image, and the output is the recognized emotional state (e.g., "stressed"). This process uses image processing and a machine learning model for emotion recognition.

[2033] Step 3:

[2034] The device sends the recognized emotional state and basic user information (ID and name) to the server in JSON format. The input is the emotional state and user information, and the output is the transmission of JSON data to the server. This process involves data format conversion and sending an HTTP request.

[2035] Step 4:

[2036] The server parses the received JSON data to obtain the user's emotional state and basic information. Based on the parsed data, it invokes a generative artificial intelligence system to generate an appropriate training module. The input is the received JSON data, and the output is the generated training module. This process involves data analysis and invoking an AI model.

[2037] Step 5:

[2038] The server uses a separate AI-powered talk generation mechanism to generate customer service dialogue based on the user's emotional state and basic information. The input consists of user information, situation information, and emotional state, while the output is the generated customer service dialogue. This process involves data analysis and AI model calls.

[2039] Step 6:

[2040] The server returns the generated training module and customer interaction dialogue to the terminal in JSON format. The input is the generated training module and customer interaction dialogue, and the output is the JSON response to the terminal. This process involves data format conversion and sending of an HTTP response.

[2041] Step 7:

[2042] The terminal analyzes the training module and customer interaction dialogue received from the server and displays them on the smart glasses' display. The input is JSON data from the server, and the output is the training module and customer interaction dialogue displayed on the screen. This process involves data analysis and display operations.

[2043] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2044] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2045] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2046] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2047] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2048] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2049] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2050] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2051] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2052] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2053] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2054] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2055] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2056] 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.

[2057] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2058] The following types of processors can be us...

Claims

1. A system aimed at standardizing the skills of sales staff and improving productivity, A generative artificial intelligence means for generating training modules based on information from sales staff, Information processing device means for providing the generated training module to sales staff, A talk generation artificial intelligence means that generates customer service dialogue according to the information and situation of the sales staff, An information processing device that provides the generated customer interaction script to the sales staff, A system that includes this.

2. The system according to claim 1, characterized in that a generative artificial intelligence means generates training modules based on the communication skills, product knowledge, and problem-solving abilities of sales staff.

3. The system according to claim 1, characterized in that the artificial intelligence means for generating conversations generates greetings, product descriptions, and question responses according to the name of the sales staff and the customer's situation.

Images