system

Abstract

Provide a system. [Solution] a means for accepting input from employees; and A means for passing the received input to a natural language processing engine; A way to provide employees with answers derived from the natural language processing engine; A system including:

Description

[Technical Field]

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

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

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

[0004] There is an environment where it is difficult for employees to discuss their career plans or personal concerns at work, which can lead to feelings of loneliness and stress building up. Furthermore, tight schedules and interpersonal issues make it difficult for employees to find time to consult with their superiors, resulting in a decline in motivation and an increase in turnover. It is necessary to solve these issues, address the concerns of each employee, and improve the health and productivity of the workplace. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting input from employees, a means for passing the accepted input to a natural language processing engine, and a means for providing the employee with a response obtained from the natural language processing engine. The system also includes a means for identifying that the input is a consultation about a problem, enabling the system to provide a more appropriate response. Furthermore, the system includes a means for reducing the time spent consulting with superiors, thereby reducing the burden on management and aiming to resolve employees' concerns and improve their motivation.

[0006] "Employee" refers to an individual who belongs to a company or organization and is employed to carry out work.

[0007] "Means for accepting input" refers to the interface or tool that employees use to send text or data to the system.

[0008] A "natural language processing engine" refers to a program or algorithm that analyzes input natural language (language used by humans on a daily basis), understands its meaning, and generates an appropriate response.

[0009] "Means for providing answers to employees" refers to the interface or mechanism for displaying or notifying employees of advice or answers generated by the natural language processing engine.

[0010] "Measures to reduce the time spent consulting with superiors" refers to methods or systems that provide alternative support or counseling to reduce the need for employees to consult with their superiors directly.

[0011] "Management load" refers to the time and effort that supervisors and managers spend instructing employees, counseling them on their problems, and resolving their issues.

[0012] "Improving motivation" refers to increasing employees' enthusiasm and efficiency in their work.

[0013] "Employee turnover rate" refers to the percentage of employees who leave a company or organization within a certain period of time.

[0014] "Career planning" refers to an employee making future plans regarding their professional life and work history.

[0015] "Personal worries" refer to private problems and stress that employees face as individuals. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system that provides advice 24 hours a day regarding workplace worries and personal problems that employees have, and contributes to the mental care and motivation of employees.

[0038] System Overview

[0039] The system includes a terminal for employees to input their concerns, a server that processes the concerns, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed by the natural language processing engine and appropriate advice is returned.

[0040] Program processing

[0041] User

[0042] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0043] Terminal

[0044] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format. The request is sent to a URL set on the server.

[0045] server

[0046] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's concerns.

[0047] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0048] server

[0049] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0050] Terminal

[0051] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0052] Specific examples

[0053] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0054] In this way, the system provides an effective means for quickly resolving employee concerns, improving workplace health and productivity.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0058] Step 2:

[0059] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, like this:

[0060] json

[0061] {

[0062] "message": "Recently, I've been feeling stressed about relationships at work."

[0063] }

[0064] The terminal sends this request to the server.

[0065] Step 3:

[0066] The server receives the HTTP POST request and extracts the user input message from the request body.

[0067] Step 4:

[0068] The server sends the extracted message to the natural language processing engine. Specifically, it sends the message by calling the API as follows:

[0069] python

[0070] response = openai.Completion.create(

[0071] engine="davinci",

[0072] prompt=f"The user is having trouble with '{user_input}'. Please provide appropriate advice.",

[0073] max_tokens=150

[0074] )

[0075] Step 5:

[0076] A natural language processing engine analyzes the received message and generates appropriate advice, such as "To improve communication with colleagues, it is important to maintain open dialogue and increase opportunities for feedback."

[0077] Step 6:

[0078] The natural language processing engine returns the generated advice to the server.

[0079] Step 7:

[0080] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0081] json

[0082] {

[0083] "advice": "To improve communication with colleagues, it's important to foster open dialogue and increase opportunities for feedback."

[0084] }

[0085] Step 8:

[0086] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] In today's workplaces, employees are increasingly experiencing stress and worries, creating a need for systems that can quickly and appropriately address these issues. Traditional methods of dealing with issues through dialogue with the HR department or superiors often result in delayed responses and require a certain amount of time for consultation, making it difficult to resolve issues efficiently. This can lead to problems with employee mental health and a decline in motivation.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for accepting input from employees, means for transmitting the accepted input content to the server, means for the server to pass the input content to a natural language processing engine and generate a prompt sentence, and means for the server to receive advice obtained from the natural language processing engine and provide it to the employee, thereby making it possible to quickly and effectively resolve the worries and stress of employees.

[0092] An "employee" is an individual employed by an organization or company to perform work.

[0093] "Input" refers to the act of an employee providing text or information to the system.

[0094] "Acceptance means" refers to the hardware and software used to collect and process employee input.

[0095] A "server" is a computer system on a network that processes data and runs programs.

[0096] A "natural language processing engine" is a program and algorithm for analyzing input linguistic data and generating appropriate responses.

[0097] A "prompt sentence" is a formatted text that provides instructions to a natural language processing engine.

[0098] "Advice" refers to advice or solutions provided to employees regarding their concerns or problems.

[0099] "Means for providing" refers to the hardware and software for displaying and communicating the advice generated by the server to employees.

[0100] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. The system includes a terminal where employees can input their concerns, a server that processes the concerns, and a natural language processing engine.

[0101] System Overview

[0102] 1. Users

[0103] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0104] 2. Terminal

[0105] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format, and the destination URL is set on the server.

[0106] 3. Server

[0107] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's inputted problem.

[0108] 4. Natural Language Processing Engine

[0109] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0110] 5. Server

[0111] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0112] 6. Terminal

[0113] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0114] Specific examples

[0115] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0116] Prompt Sentence Examples

[0117] If an employee enters, "Recently, the pressure at work has increased and I feel stressed," the following prompt sentence is used as input to the generative AI model:

[0118] What specific advice would you give to employees who are feeling stressed due to increased pressure at work?

[0119]

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1:

[0122] The user inputs their concerns

[0123] The user (employee) opens the dedicated application and enters their concerns in a text box. For example, they might enter something like, "Recently, the pressure at work has increased and I feel stressed." The entered concerns are saved in the application's input field and are ready to be sent to the server.

[0124] Step 2:

[0125] The device sends input to the server

[0126] The device (PC or smartphone) reads the text of the problem entered by the user in the input field and sends it to the server as an HTTP POST request. The input data is converted to JSON format and included in the body of the HTTP request. The destination URL is the server's endpoint. The device outputs JSON format data, which the server receives as input.

[0127] Step 3:

[0128] The server receives and analyzes the message

[0129] The server receives an HTTP POST request sent from the terminal. It extracts the message from the body of the request and prepares to pass it to the natural language processing engine. At this time, the server checks the contents of the message to ensure that no data is missing. The server's input is the message in the body of the HTTP request, and its output is a prompt sentence to pass to the natural language processing engine.

[0130] Step 4:

[0131] The server makes an API call to the natural language processing engine.

[0132] The server generates a prompt sentence based on the received message and sends it to the API endpoint of the natural language processing engine. For example, the prompt sentence might be, "Please give some specific advice to an employee who is feeling stressed due to increasing pressure at work." The input to the server is the extracted message, and the output is the prompt sentence sent to the natural language processing engine.

[0133] Step 5:

[0134] Natural language processing engine generates advice

[0135] The natural language processing engine analyzes the received prompt sentence and generates appropriate advice using a knowledge base. For example, it generates advice such as, "If you are feeling pressure at work, we recommend that you first review your work priorities and focus on the most important tasks." The input to the natural language processing engine is the prompt sentence, and the output is the generated advice.

[0136] Step 6:

[0137] The server receives the advice and reformats it.

[0138] The server receives the advice generated by the natural language processing engine and converts it into JSON format. It prepares the converted data to be sent to the terminal as an HTTP response. The input of the server is the generated advice, and the output is the response data in JSON format.

[0139] Step 7:

[0140] The device receives and displays the advice

[0141] The terminal receives an HTTP response from the server and extracts the advice text data from the response body. The extracted advice is displayed in a specific display area within the application, allowing the user to obtain advice as a specific solution. The input of the terminal is the response received from the server, and the output is the advice to be displayed.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] In today's workplace, mental health concerns and stress are on the rise among employees, requiring prompt and appropriate responses. However, with limited time and resources to consult with superiors or professional counselors, there is a lack of effective ways to resolve employees' concerns. To solve this problem, an automated system that can respond to employees' concerns 24 hours a day is needed.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model, thereby enabling the employee's concern to be quickly analyzed and appropriate advice to be provided immediately.

[0147] "Means for accepting input from employees" refers to devices or software that provide an interface for employees to input their concerns or questions, and that have the function of accepting that input.

[0148] "Means for passing accepted input content to the natural language processing engine" refers to devices or software that have the function of converting the content entered by employees into an appropriate format and sending it to the natural language processing engine.

[0149] The "means for providing employees with answers obtained from the natural language processing engine" refers to a device or software that has the function of notifying employees of advice generated by the natural language processing engine.

[0150] "Means for using a generative AI model to analyze input concerns" refers to devices or software that have the function of utilizing a generative AI model to analyze concerns or consultation details input by employees.

[0151] "Means for creating and sending prompt sentences to a generative AI model" refers to devices or software that have the function of creating prompt sentences to request an appropriate analysis from a generative AI model and sending those prompt sentences to the model.

[0152] This invention is a system that provides 24-hour advice to employees regarding workplace concerns and personal problems. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model.

[0153] System configuration

[0154] 1. Accept employee input by:

[0155] Users use devices such as smartphones or computers to enter their concerns into a text box within a dedicated application. This application is built using React Native. For example, an employee might enter a concern such as, "Recently, I've been feeling more stressed due to work pressure."

[0156] 2. A way to pass the received input to the natural language processing engine:

[0157] The terminal wraps the input content in JSON format and sends it to the server as an HTTP POST request, which is received by a server built using Node.js and Express.

[0158] 3. How to provide answers from the natural language processing engine to employees:

[0159] The server analyzes the received request and forwards the input to OpenAI's GPT-4 API. The generative AI model receives a prompt (e.g., "Please provide advice for the following problem: I've recently been feeling more stressed due to work pressure") and generates appropriate advice.

[0160] 4. How to use generative AI models to analyze input concerns:

[0161] The generative AI model analyzes the problem and generates appropriate advice, such as "To reduce work pressure, it is effective to take regular breaks and focus on important tasks."

[0162] 5. How to create and send prompts to a generative AI model:

[0163] The server creates a prompt and sends it to the OpenAI GPT-4 API. The generated advice is returned to the server in JSON format, and the server then forwards it to the device.

[0164] Specific examples

[0165] Consider the case where an employee inputs a concern into this system: "Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." In this case, the device sends the message to the server, which passes it on to the natural language processing engine. The natural language processing engine generates advice based on the prompt: "Please provide advice for the following concern: Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." The final advice generated and provided to the employee is: "To improve communication with colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue."

[0166] This system is expected to improve workplace health and productivity by allowing employees to receive prompt and appropriate advice anytime, anywhere.

[0167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0168] Step 1:

[0169] The user opens a dedicated application on their smartphone or computer and enters their concerns into a text box. For example, the input data might be, "Recently, the pressure at work has increased and I feel stressed." This text data is entered into the device, and the device is ready to proceed to the next step.

[0170] Step 2:

[0171] The device wraps the input text data in JSON format as an HTTP POST request and sends it to the server. The input of this request is the employee's concerns, and the output is the data sent via communication to the server. Specifically, the device sends a request to the API endpoint.

[0172] Step 3:

[0173] The server receives an HTTP POST request sent from the device and extracts the input message from the request body. The input is the text data of the problem received in JSON format, and the output is the extracted message. Specifically, the server analyzes the received data and stores the message in the appropriate variable.

[0174] Step 4:

[0175] The server creates a prompt from the extracted text message to be passed to the generative AI model, specifically the OpenAI GPT-4 API, and sends an API request. The input is the text data of the employee's concerns, and the output is the generated prompt and the result of sending the API request. Specifically, the server incorporates the content of the concerns into the prompt and sends it to the GPT-4 API.

[0176] Step 5:

[0177] The generative AI model (GPT-4) analyzes the received prompt and generates appropriate advice. The input is the prompt sent from the server, and the output is the generated advice text. Specifically, the generative AI model performs natural language processing to derive the optimal advice.

[0178] Step 6:

[0179] The server receives the advice obtained from the generative AI model, converts it to JSON format, and sends it to the terminal as an HTTP response. The input is the text of the advice from the generative AI model, and the output is the data to be sent to the terminal. Specifically, the server wraps the advice in JSON format and sends it back to the terminal.

[0180] Step 7:

[0181] The terminal displays the received advice within the application. The input is the JSON data of the advice received from the server, and the output is the advice displayed in a form that the user can visually confirm. Specifically, the terminal analyzes the received data and displays the advice in the user interface.

[0182] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0183] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. In particular, by combining it with an emotion engine, it is possible to recognize employees' emotional states and provide more appropriate advice.

[0184] System Overview

[0185] The system includes a terminal for employees to input their concerns, a server that processes the concerns, an emotion engine, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed through the emotion engine and the natural language processing engine, and appropriate advice is returned.

[0186] Program processing

[0187] User

[0188] Employees open a dedicated application and enter their concerns. For example, they can write, "Recently, I've been feeling stressed about interpersonal relationships at work" in the text box.

[0189] Terminal

[0190] The device (employee's PC or smartphone) receives the inputted concern. Then, it generates an HTTP POST request and sends it to the server. This request contains the user's input in JSON format as shown below.

[0191] json

[0192] {

[0193] "message": "Recently, I've been feeling stressed about relationships at work."

[0194] }

[0195] server

[0196] The server receives the HTTP POST request sent from the terminal and extracts the user's input message from the request body.

[0197] The server first passes the extracted message to an emotion engine, which analyzes the user's emotional state. For example, the emotion engine detects emotions such as "stress" or "anxiety" from the input message.

[0198] Next, the server passes the emotion information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotion information.

[0199] python

[0200] response = openai.Completion.create(

[0201] engine="davinci",

[0202] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0203] max_tokens=150

[0204] )

[0205] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0206] The server receives the generated advice, converts it into JSON format, and sends it to the terminal as an HTTP response.

[0207] json

[0208] {

[0209] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0210] }

[0211] Terminal

[0212] The device receives the response from the server and displays the advice within the application, which the user can then confirm and implement.

[0213] Specific examples

[0214] For example, suppose an employee inputs into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion engine to recognize emotions such as "irritation" or "anxiety." The natural language processing engine then generates advice incorporating the emotional information, which is returned to the device via the server. Ultimately, the system provides the employee with the following advice: "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0215] In this way, by combining this system with an emotion engine, it is possible to gain a deeper understanding of employees' concerns and provide more appropriate advice, thereby contributing to improving workplace health and productivity.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0219] Step 2:

[0220] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, as follows:

[0221] json

[0222] {

[0223] "message": "Recently, I've been feeling stressed about relationships at work."

[0224] }

[0225] The terminal sends this request to the server.

[0226] Step 3:

[0227] The server receives the HTTP POST request and extracts the user input message from the request body.

[0228] Step 4:

[0229] The server passes the extracted message to the emotion engine, which analyzes the user's emotional state. For example, the emotion engine can detect emotions such as "stress" or "anxiety" from the input message.

[0230] Step 5:

[0231] The emotion engine returns the analyzed emotion information to the server. For example, it returns information such as "The user's emotion is stress."

[0232] Step 6:

[0233] The server passes the emotional information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotional information.

[0234] python

[0235] response = openai.Completion.create(

[0236] engine="davinci",

[0237] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0238] max_tokens=150

[0239] )

[0240] For example, the prompt may read, "The user is worried about 'Recently, I've been feeling stressed by interpersonal relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0241] Step 7:

[0242] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0243] Step 8:

[0244] The natural language processing engine returns the generated advice to the server.

[0245] Step 9:

[0246] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0247] json

[0248] {

[0249] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0250] }

[0251] Step 10:

[0252] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0253] Example 2

[0254] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0255] Previous systems lacked support for dealing with workplace worries and personal problems, and it was particularly difficult to take emotional factors into account. This made it difficult to provide appropriate advice quickly, creating challenges for employees' mental health and motivation. Furthermore, in many cases, it took time to consult with superiors, resulting in a decline in productivity.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0257] In this invention, the server includes a means for accepting input from employees, a means for passing the accepted input to an emotion analysis engine, a means for passing emotional information obtained from the emotion analysis engine to a natural language processing engine, and a means for providing the employee with a response obtained from the natural language processing engine. This makes it possible to appropriately analyze the emotional state of employees and quickly provide specific advice based on that analysis. It also reduces the time spent consulting with superiors, contributing to the mental health of employees and improving their motivation.

[0258] "Means for accepting input from employees" refers to a function that provides an interface that allows employees to input their concerns and problems in text format using a dedicated application.

[0259] The "means of passing accepted input content to the emotion analysis engine" is a function that converts text data entered by employees into an appropriate format and sends it to the emotion analysis engine.

[0260] An "emotion analysis engine" is a software module that analyzes a user's emotional state from input text, identifying emotions such as "stress" or "anxiety," for example.

[0261] The "means for passing emotional information obtained from the emotion analysis engine to the natural language processing engine" is a function for receiving emotional information output from the emotion analysis engine and passing it to the natural language processing engine.

[0262] A "natural language processing engine" is a software module that generates appropriate advice based on emotional information and input concerns.

[0263] The "means for providing employees with answers obtained from the natural language processing engine" is a function for displaying advice generated from the natural language processing engine to employees.

[0264] The "system" refers to a comprehensive configuration that includes the device where employees input data, the server, the emotion analysis engine, the natural language processing engine, and the software and hardware that connects them.

[0265] "Means for identifying that the input content is a problem or consultation" is a function for automatically determining whether the text entered by an employee is a problem or consultation.

[0266] "Measures aimed at reducing the time spent consulting with superiors" are ideas and techniques that reduce the time employees spend directly consulting with superiors and enable efficient problem-solving.

[0267] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems. By combining an emotion analysis engine and a natural language processing engine, this system is able to recognize employees' emotional states and provide more appropriate advice.

[0268] System configuration

[0269] The system includes a terminal for employees to input their concerns, a server for processing the concerns, a sentiment analysis engine, and a natural language processing engine.

[0270] Terminal

[0271] The devices are PCs or smartphones used by employees. Employees open a dedicated application and input their concerns or problems. This input is sent to the server as an HTTP POST request.

[0272] server

[0273] The server receives the HTTP POST request sent from the device and extracts the user's input message from the request body. It then passes this message to an emotion analysis engine to analyze the user's emotional state. The emotion analysis engine detects emotions such as "stress" and "anxiety" from the input message.

[0274] The emotion information obtained from the emotion analysis engine is passed to the natural language processing engine. The server uses OpenAI's API to generate prompts as follows:

[0275] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0276] The natural language processing engine generates optimal advice based on the prompts and sends it back to the server, which converts the advice into JSON format and sends it to the device as an HTTP response.

[0277] Sentiment Analysis Engine

[0278] The sentiment analysis engine includes an algorithm for analyzing input text data and identifying the emotional state of the user. The algorithm uses natural language processing techniques to identify the emotional state.

[0279] Natural Language Processing Engine

[0280] The natural language processing engine is a software module that generates appropriate advice based on the emotional information obtained from the emotion analysis engine and the user's concerns. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-3 (registered trademark)).

[0281] Specific examples

[0282] For example, an employee might input into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion analysis engine to recognize emotions such as "irritation" or "anxiety." The server then uses a natural language processing engine to generate advice that incorporates the emotional information. The generated advice is sent back to the device via the server and provided to the employee in the form of, "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0283] This system allows employees to receive appropriate advice at any time, reducing the amount of time they spend consulting with their superiors and improving their mental health, which is expected to improve workplace health and productivity.

[0284] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0285] Step 1:

[0286] The user opens the dedicated application and enters their concerns into a text box. For example, they might enter, "Recently, I've been feeling stressed about interpersonal relationships at work." This input is then passed to the next step.

[0287] Step 2:

[0288] The device receives the text data entered by the user, generates an HTTP POST request, and sends it to the server. This request contains the entered text in JSON format, for example:

[0289] json

[0290] {

[0291] "message": "Recently, I've been feeling stressed about relationships at work."

[0292] }

[0293] This request is passed to the server.

[0294] Step 3:

[0295] The server receives the HTTP POST request sent from the device. It extracts the user's input message from the request body and passes it to the emotion analysis engine. The server then sends the input data to the emotion analysis engine for analysis.

[0296] Step 4:

[0297] The emotion analysis engine analyzes the user's emotional state from the received input message. For example, the emotion analysis engine detects emotions such as "stress" or "anxiety." The analysis result is returned to the server in the following JSON format:

[0298] json

[0299] {

[0300] "emotion": "stress"

[0301] }

[0302] Step 5:

[0303] The server receives the emotion information obtained from the emotion analysis engine and passes it to the natural language processing engine. Specifically, it creates the following prompt to generate a prompt sentence and call the API.

[0304] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0305] This prompt is sent to a natural language processing engine.

[0306] Step 6:

[0307] The natural language processing engine analyzes the prompts and generates optimal advice based on the user's concerns and emotions. For example, it might generate advice such as, "To improve communication with your colleagues, it's important to set up regular opportunities for feedback and maintain open dialogue. Also, pay attention to your own stress management." This advice is then returned to the server.

[0308] Step 7:

[0309] The server receives advice from the natural language processing engine, converts it into JSON format, and sends it to the terminal as an HTTP response. For example, the following data is sent to the terminal:

[0310] json

[0311] {

[0312] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0313] }

[0314] Step 8:

[0315] The device receives the response from the server and displays the advice within the application. The user can confirm and put into practice this advice, thereby gaining concrete ways to deal with worries and stress in the workplace.

[0316] (Application example 2)

[0317] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] In today's workplace, improving employee mental health and motivation is an important issue. However, especially in factories, employees often work 24 hours a day, limiting the time they have to consult with their superiors or colleagues. It is also difficult to grasp the psychological burden of workplace relationships and work-related stress in real time and provide appropriate advice. Therefore, there is a need for a system that can quickly respond to employees' concerns and provide appropriate advice that takes their emotions into consideration.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from an employee, means for passing the accepted input content to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice as voice. This makes it possible to grasp the employee's concerns in real time and provide appropriate advice that takes emotions into consideration.

[0320] An "employee" is a worker who works for a company or organization and is employed to carry out duties.

[0321] "Means for accepting input" refers to the interface or system for receiving concerns and questions from employees.

[0322] A "natural language processing engine" is a program that analyzes input text data and understands its meaning and intent.

[0323] "Means for providing answers" refers to the methods and devices used to communicate advice and answers generated by the natural language processing engine to employees.

[0324] "Voice-to-text conversion means" refers to any technology or device used to convert an employee's speech into digital text.

[0325] An "emotion analysis engine" is a program for identifying and analyzing emotions and psychological states from text data.

[0326] "Generative AI model" refers to an artificial intelligence model that generates appropriate advice based on input data.

[0327] "Voice output means" refers to a device or system that converts the generated text advice into voice and transmits it to employees.

[0328] A system for carrying out this invention provides prompt and appropriate advice to employees regarding mental worries and stress. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice by voice.

[0329] Server Processing

[0330] The server receives input data sent from the device and passes it to a sentiment analysis engine to extract emotional information. This sentiment analysis engine uses Azure® Cognitive Services or similar. The server then queries a natural language processing engine along with the emotional information to generate appropriate advice. This generation uses a generative AI model such as OpenAI's GPT-3.

[0331] For example, if the server receives the input, "Recently, working late-night shifts has been tough and mentally stressful," the emotion analysis engine extracts "stress" as emotional information.The server then sends the following prompt sentence to the generative AI model:

[0332] Example prompt sentence:

[0333] A user is worried about 'lately working late-night shifts has been tough and mentally exhausting' and the emotion they are feeling is 'stress'. Please provide appropriate advice.

[0334] Terminal handling

[0335] The device receives the employee's voice input and converts this voice into text using Google's (registered trademark) speech recognition API, etc. It also receives the generated advice from the server and provides it to the employee in audio format using Google Text-to-Speech, etc.

[0336] For example, if an employee makes a voice input such as "I've been feeling stressed about interpersonal relationships at work recently," the device converts this voice into text and sends it to the server. After receiving the generated advice from the server, the device converts the advice into voice and conveys it to the employee.

[0337] How users use it

[0338] Users talk about their concerns into a microphone built into the robot, and the system converts the speech into text and sends it to the server. The server uses emotion analysis and generative AI models to generate appropriate advice, which the device then relays to the user via voice. This process allows users to receive specific, emotionally appropriate advice in real time.

[0339] In this way, this system can consistently perform everything from voice input to emotion analysis, advice generation, and voice output, making it possible to respond quickly and appropriately to the various workplace worries and stresses that employees face.

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] The user inputs their concerns by voice. For example, they might say, "Recently, I've been feeling stressed about interpersonal relationships at work." The input is voice data.

[0343] Step 2:

[0344] The device receives voice data and converts it into text using Google's speech recognition API. Specifically, the voice data is sent to the speech recognition engine and text data is obtained. The output is text data.

[0345] Step 3:

[0346] The device sends text data to the server as an HTTP POST request. The request content includes the user's text input. The output is the text data sent to the server.

[0347] Step 4:

[0348] The server passes the received text data to a sentiment analysis engine (e.g., Azure Cognitive Services) to extract emotional information. The sentiment analysis engine identifies emotions (e.g., "stress" or "anxiety") from the text data. The output is emotional information.

[0349] Step 5:

[0350] The server passes the emotion information and text data to a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate advice. The generative AI model creates advice based on the given prompt. The output is the advice text data.

[0351] Step 6:

[0352] The server sends the generated advice to the terminal as an HTTP response. The response content includes the generated advice. The output is the text data of the advice sent to the terminal.

[0353] Step 7:

[0354] The device converts the received text data of advice into speech using the Google Text-to-Speech API. Specifically, the text data is sent to a speech synthesis engine, and speech data is obtained. The output is speech data.

[0355] Step 8:

[0356] The terminal provides the generated voice data to the user through a speaker, and the user receives the advice by voice. The output is the voice advice provided to the user.

[0357] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0358] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0359] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0360] [Second embodiment]

[0361] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0362] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0363] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0364] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0365] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0366] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0367] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0368] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0369] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0370] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0371] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0372] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0373] This invention is a system that provides advice 24 hours a day regarding workplace worries and personal problems that employees have, and contributes to the mental care and motivation of employees.

[0374] System Overview

[0375] The system includes a terminal for employees to input their concerns, a server that processes the concerns, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed by the natural language processing engine and appropriate advice is returned.

[0376] Program processing

[0377] User

[0378] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0379] Terminal

[0380] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format. The request is sent to a URL set on the server.

[0381] server

[0382] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's concerns.

[0383] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0384] server

[0385] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0386] Terminal

[0387] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0388] Specific examples

[0389] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0390] In this way, the system provides an effective means for quickly resolving employee concerns, improving workplace health and productivity.

[0391] The processing flow will be explained below.

[0392] Step 1:

[0393] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0394] Step 2:

[0395] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, like this:

[0396] json

[0397] {

[0398] "message": "Recently, I've been feeling stressed about relationships at work."

[0399] }

[0400] The terminal sends this request to the server.

[0401] Step 3:

[0402] The server receives the HTTP POST request and extracts the user input message from the request body.

[0403] Step 4:

[0404] The server sends the extracted message to the natural language processing engine. Specifically, it sends the message by calling the API as follows:

[0405] python

[0406] response = openai.Completion.create(

[0407] engine="davinci",

[0408] prompt=f"The user is having trouble with '{user_input}'. Please provide appropriate advice.",

[0409] max_tokens=150

[0410] )

[0411] Step 5:

[0412] A natural language processing engine analyzes the received message and generates appropriate advice, such as "To improve communication with colleagues, it is important to maintain open dialogue and increase opportunities for feedback."

[0413] Step 6:

[0414] The natural language processing engine returns the generated advice to the server.

[0415] Step 7:

[0416] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0417] json

[0418] {

[0419] "advice": "To improve communication with colleagues, it's important to foster open dialogue and increase opportunities for feedback."

[0420] }

[0421] Step 8:

[0422] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0423] Example 1

[0424] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0425] In today's workplaces, employees are increasingly experiencing stress and worries, creating a need for systems that can quickly and appropriately address these issues. Traditional methods of dealing with issues through dialogue with the HR department or superiors often result in delayed responses and require a certain amount of time for consultation, making it difficult to resolve issues efficiently. This can lead to problems with employee mental health and a decline in motivation.

[0426] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0427] In this invention, the server includes means for accepting input from employees, means for transmitting the accepted input content to the server, means for the server to pass the input content to a natural language processing engine and generate a prompt sentence, and means for the server to receive advice obtained from the natural language processing engine and provide it to the employee, thereby making it possible to quickly and effectively resolve the worries and stress of employees.

[0428] An "employee" is an individual employed by an organization or company to perform work.

[0429] "Input" refers to the act of an employee providing text or information to the system.

[0430] "Acceptance means" refers to the hardware and software used to collect and process employee input.

[0431] A "server" is a computer system on a network that processes data and runs programs.

[0432] A "natural language processing engine" is a program and algorithm for analyzing input linguistic data and generating appropriate responses.

[0433] A "prompt sentence" is a formatted text that provides instructions to a natural language processing engine.

[0434] "Advice" refers to advice or solutions provided to employees regarding their concerns or problems.

[0435] "Means for providing" refers to the hardware and software for displaying and communicating the advice generated by the server to employees.

[0436] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. The system includes a terminal where employees can input their concerns, a server that processes the concerns, and a natural language processing engine.

[0437] System Overview

[0438] 1. Users

[0439] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0440] 2. Terminal

[0441] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format, and the destination URL is set on the server.

[0442] 3. Server

[0443] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's inputted problem.

[0444] 4. Natural Language Processing Engine

[0445] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0446] 5. Server

[0447] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0448] 6. Terminal

[0449] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0450] Specific examples

[0451] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0452] Prompt Sentence Examples

[0453] If an employee enters, "Recently, the pressure at work has increased and I feel stressed," the following prompt sentence is used as input to the generative AI model:

[0454] What specific advice would you give to employees who are feeling stressed due to increased pressure at work?

[0455]

[0456] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0457] Step 1:

[0458] The user inputs their concerns

[0459] The user (employee) opens the dedicated application and enters their concerns in a text box. For example, they might enter something like, "Recently, the pressure at work has increased and I feel stressed." The entered concerns are saved in the application's input field and are ready to be sent to the server.

[0460] Step 2:

[0461] The device sends input to the server

[0462] The device (PC or smartphone) reads the text of the problem entered by the user in the input field and sends it to the server as an HTTP POST request. The input data is converted to JSON format and included in the body of the HTTP request. The destination URL is the server's endpoint. The device outputs JSON format data, which the server receives as input.

[0463] Step 3:

[0464] The server receives and analyzes the message

[0465] The server receives an HTTP POST request sent from the terminal. It extracts the message from the body of the request and prepares to pass it to the natural language processing engine. At this time, the server checks the contents of the message to ensure that no data is missing. The server's input is the message in the body of the HTTP request, and its output is a prompt sentence to pass to the natural language processing engine.

[0466] Step 4:

[0467] The server makes an API call to the natural language processing engine.

[0468] The server generates a prompt sentence based on the received message and sends it to the API endpoint of the natural language processing engine. For example, the prompt sentence might be, "Please give some specific advice to an employee who is feeling stressed due to increasing pressure at work." The input to the server is the extracted message, and the output is the prompt sentence sent to the natural language processing engine.

[0469] Step 5:

[0470] Natural language processing engine generates advice

[0471] The natural language processing engine analyzes the received prompt sentence and generates appropriate advice using a knowledge base. For example, it generates advice such as, "If you are feeling pressure at work, we recommend that you first review your work priorities and focus on the most important tasks." The input to the natural language processing engine is the prompt sentence, and the output is the generated advice.

[0472] Step 6:

[0473] The server receives the advice and reformats it.

[0474] The server receives the advice generated by the natural language processing engine and converts it into JSON format. It prepares the converted data to be sent to the terminal as an HTTP response. The input of the server is the generated advice, and the output is the response data in JSON format.

[0475] Step 7:

[0476] The device receives and displays the advice

[0477] The terminal receives an HTTP response from the server and extracts the advice text data from the response body. The extracted advice is displayed in a specific display area within the application, allowing the user to obtain advice as a specific solution. The input of the terminal is the response received from the server, and the output is the advice to be displayed.

[0478] (Application example 1)

[0479] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0480] In today's workplace, mental health concerns and stress are on the rise among employees, requiring prompt and appropriate responses. However, with limited time and resources to consult with superiors or professional counselors, there is a lack of effective ways to resolve employees' concerns. To solve this problem, an automated system that can respond to employees' concerns 24 hours a day is needed.

[0481] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0482] In this invention, the server includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model, thereby enabling the employee's concern to be quickly analyzed and appropriate advice to be provided immediately.

[0483] "Means for accepting input from employees" refers to devices or software that provide an interface for employees to input their concerns or questions, and that have the function of accepting that input.

[0484] "Means for passing accepted input content to the natural language processing engine" refers to devices or software that have the function of converting the content entered by employees into an appropriate format and sending it to the natural language processing engine.

[0485] The "means for providing employees with answers obtained from the natural language processing engine" refers to a device or software that has the function of notifying employees of advice generated by the natural language processing engine.

[0486] "Means for using a generative AI model to analyze input concerns" refers to devices or software that have the function of utilizing a generative AI model to analyze concerns or consultation details input by employees.

[0487] "Means for creating and sending prompt sentences to a generative AI model" refers to devices or software that have the function of creating prompt sentences to request an appropriate analysis from a generative AI model and sending those prompt sentences to the model.

[0488] This invention is a system that provides 24-hour advice to employees regarding workplace concerns and personal problems. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model.

[0489] System configuration

[0490] 1. Accept employee input by:

[0491] Users use devices such as smartphones or computers to enter their concerns into a text box within a dedicated application. This application is built using React Native. For example, an employee might enter a concern such as, "Recently, I've been feeling more stressed due to work pressure."

[0492] 2. A way to pass the received input to the natural language processing engine:

[0493] The terminal wraps the input content in JSON format and sends it to the server as an HTTP POST request, which is received by a server built using Node.js and Express.

[0494] 3. How to provide answers from the natural language processing engine to employees:

[0495] The server analyzes the received request and forwards the input to OpenAI's GPT-4 API. The generative AI model receives a prompt (e.g., "Please provide advice for the following problem: I've recently been feeling more stressed due to work pressure") and generates appropriate advice.

[0496] 4. How to use generative AI models to analyze input concerns:

[0497] The generative AI model analyzes the problem and generates appropriate advice, such as "To reduce work pressure, it is effective to take regular breaks and focus on important tasks."

[0498] 5. How to create and send prompts to a generative AI model:

[0499] The server creates a prompt and sends it to the OpenAI GPT-4 API. The generated advice is returned to the server in JSON format, and the server then forwards it to the device.

[0500] Specific examples

[0501] Consider the case where an employee inputs a concern into this system: "Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." In this case, the device sends the message to the server, which passes it on to the natural language processing engine. The natural language processing engine generates advice based on the prompt: "Please provide advice for the following concern: Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." The final advice generated and provided to the employee is: "To improve communication with colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue."

[0502] This system is expected to improve workplace health and productivity by allowing employees to receive prompt and appropriate advice anytime, anywhere.

[0503] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0504] Step 1:

[0505] The user opens a dedicated application on their smartphone or computer and enters their concerns into a text box. For example, the input data might be, "Recently, the pressure at work has increased and I feel stressed." This text data is entered into the device, and the device is ready to proceed to the next step.

[0506] Step 2:

[0507] The device wraps the input text data in JSON format as an HTTP POST request and sends it to the server. The input of this request is the employee's concerns, and the output is the data sent via communication to the server. Specifically, the device sends a request to the API endpoint.

[0508] Step 3:

[0509] The server receives an HTTP POST request sent from the device and extracts the input message from the request body. The input is the text data of the problem received in JSON format, and the output is the extracted message. Specifically, the server analyzes the received data and stores the message in the appropriate variable.

[0510] Step 4:

[0511] The server creates a prompt from the extracted text message to be passed to the generative AI model, specifically the OpenAI GPT-4 API, and sends an API request. The input is the text data of the employee's concerns, and the output is the generated prompt and the result of sending the API request. Specifically, the server incorporates the content of the concerns into the prompt and sends it to the GPT-4 API.

[0512] Step 5:

[0513] The generative AI model (GPT-4) analyzes the received prompt and generates appropriate advice. The input is the prompt sent from the server, and the output is the generated advice text. Specifically, the generative AI model performs natural language processing to derive the optimal advice.

[0514] Step 6:

[0515] The server receives the advice obtained from the generative AI model, converts it to JSON format, and sends it to the terminal as an HTTP response. The input is the text of the advice from the generative AI model, and the output is the data to be sent to the terminal. Specifically, the server wraps the advice in JSON format and sends it back to the terminal.

[0516] Step 7:

[0517] The terminal displays the received advice within the application. The input is the JSON data of the advice received from the server, and the output is the advice displayed in a form that the user can visually confirm. Specifically, the terminal analyzes the received data and displays the advice in the user interface.

[0518] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0519] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. In particular, by combining it with an emotion engine, it is possible to recognize employees' emotional states and provide more appropriate advice.

[0520] System Overview

[0521] The system includes a terminal for employees to input their concerns, a server that processes the concerns, an emotion engine, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed through the emotion engine and the natural language processing engine, and appropriate advice is returned.

[0522] Program processing

[0523] User

[0524] Employees open a dedicated application and enter their concerns. For example, they can write, "Recently, I've been feeling stressed about interpersonal relationships at work" in the text box.

[0525] Terminal

[0526] The device (employee's PC or smartphone) receives the inputted concern. Then, it generates an HTTP POST request and sends it to the server. This request contains the user's input in JSON format as shown below.

[0527] json

[0528] {

[0529] "message": "Recently, I've been feeling stressed about relationships at work."

[0530] }

[0531] server

[0532] The server receives the HTTP POST request sent from the terminal and extracts the user's input message from the request body.

[0533] The server first passes the extracted message to an emotion engine, which analyzes the user's emotional state. For example, the emotion engine detects emotions such as "stress" or "anxiety" from the input message.

[0534] Next, the server passes the emotion information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotion information.

[0535] python

[0536] response = openai.Completion.create(

[0537] engine="davinci",

[0538] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0539] max_tokens=150

[0540] )

[0541] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0542] The server receives the generated advice, converts it into JSON format, and sends it to the terminal as an HTTP response.

[0543] json

[0544] {

[0545] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0546] }

[0547] Terminal

[0548] The device receives the response from the server and displays the advice within the application, which the user can then confirm and implement.

[0549] Specific examples

[0550] For example, suppose an employee inputs into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion engine to recognize emotions such as "irritation" or "anxiety." The natural language processing engine then generates advice incorporating the emotional information, which is returned to the device via the server. Ultimately, the system provides the employee with the following advice: "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0551] In this way, by combining this system with an emotion engine, it is possible to gain a deeper understanding of employees' concerns and provide more appropriate advice, thereby contributing to improving workplace health and productivity.

[0552] The processing flow will be explained below.

[0553] Step 1:

[0554] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0555] Step 2:

[0556] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, as follows:

[0557] json

[0558] {

[0559] "message": "Recently, I've been feeling stressed about relationships at work."

[0560] }

[0561] The terminal sends this request to the server.

[0562] Step 3:

[0563] The server receives the HTTP POST request and extracts the user input message from the request body.

[0564] Step 4:

[0565] The server passes the extracted message to the emotion engine, which analyzes the user's emotional state. For example, the emotion engine can detect emotions such as "stress" or "anxiety" from the input message.

[0566] Step 5:

[0567] The emotion engine returns the analyzed emotion information to the server. For example, it returns information such as "The user's emotion is stress."

[0568] Step 6:

[0569] The server passes the emotional information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotional information.

[0570] python

[0571] response = openai.Completion.create(

[0572] engine="davinci",

[0573] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0574] max_tokens=150

[0575] )

[0576] For example, the prompt may read, "The user is worried about 'Recently, I've been feeling stressed by interpersonal relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0577] Step 7:

[0578] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0579] Step 8:

[0580] The natural language processing engine returns the generated advice to the server.

[0581] Step 9:

[0582] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0583] json

[0584] {

[0585] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0586] }

[0587] Step 10:

[0588] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0589] Example 2

[0590] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0591] Previous systems lacked support for dealing with workplace worries and personal problems, and it was particularly difficult to take emotional factors into account. This made it difficult to provide appropriate advice quickly, creating challenges for employees' mental health and motivation. Furthermore, in many cases, it took time to consult with superiors, resulting in a decline in productivity.

[0592] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0593] In this invention, the server includes a means for accepting input from employees, a means for passing the accepted input to an emotion analysis engine, a means for passing emotional information obtained from the emotion analysis engine to a natural language processing engine, and a means for providing the employee with a response obtained from the natural language processing engine. This makes it possible to appropriately analyze the emotional state of employees and quickly provide specific advice based on that analysis. It also reduces the time spent consulting with superiors, contributing to the mental health of employees and improving their motivation.

[0594] "Means for accepting input from employees" refers to a function that provides an interface that allows employees to input their concerns and problems in text format using a dedicated application.

[0595] The "means of passing accepted input content to the emotion analysis engine" is a function that converts text data entered by employees into an appropriate format and sends it to the emotion analysis engine.

[0596] An "emotion analysis engine" is a software module that analyzes a user's emotional state from input text, identifying emotions such as "stress" or "anxiety," for example.

[0597] The "means for passing emotional information obtained from the emotion analysis engine to the natural language processing engine" is a function for receiving emotional information output from the emotion analysis engine and passing it to the natural language processing engine.

[0598] A "natural language processing engine" is a software module that generates appropriate advice based on emotional information and input concerns.

[0599] The "means for providing employees with answers obtained from the natural language processing engine" is a function for displaying advice generated from the natural language processing engine to employees.

[0600] The "system" refers to a comprehensive configuration that includes the device where employees input data, the server, the emotion analysis engine, the natural language processing engine, and the software and hardware that connects them.

[0601] "Means for identifying that the input content is a problem or consultation" is a function for automatically determining whether the text entered by an employee is a problem or consultation.

[0602] "Measures aimed at reducing the time spent consulting with superiors" are ideas and techniques that reduce the time employees spend directly consulting with superiors and enable efficient problem-solving.

[0603] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems. By combining an emotion analysis engine and a natural language processing engine, this system is able to recognize employees' emotional states and provide more appropriate advice.

[0604] System configuration

[0605] The system includes a terminal for employees to input their concerns, a server for processing the concerns, a sentiment analysis engine, and a natural language processing engine.

[0606] Terminal

[0607] The devices are PCs or smartphones used by employees. Employees open a dedicated application and input their concerns or problems. This input is sent to the server as an HTTP POST request.

[0608] server

[0609] The server receives the HTTP POST request sent from the device and extracts the user's input message from the request body. It then passes this message to an emotion analysis engine to analyze the user's emotional state. The emotion analysis engine detects emotions such as "stress" and "anxiety" from the input message.

[0610] The emotion information obtained from the emotion analysis engine is passed to the natural language processing engine. The server uses OpenAI's API to generate prompts as follows:

[0611] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0612] The natural language processing engine generates optimal advice based on the prompts and sends it back to the server, which converts the advice into JSON format and sends it to the device as an HTTP response.

[0613] Sentiment Analysis Engine

[0614] The sentiment analysis engine includes an algorithm for analyzing input text data and identifying the emotional state of the user. The algorithm uses natural language processing techniques to identify the emotional state.

[0615] Natural Language Processing Engine

[0616] The natural language processing engine is a software module that generates appropriate advice based on the emotional information obtained from the emotion analysis engine and the user's concerns. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-3).

[0617] Specific examples

[0618] For example, an employee might input into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion analysis engine to recognize emotions such as "irritation" or "anxiety." The server then uses a natural language processing engine to generate advice that incorporates the emotional information. The generated advice is sent back to the device via the server and provided to the employee in the form of, "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0619] This system allows employees to receive appropriate advice at any time, reducing the amount of time they spend consulting with their superiors and improving their mental health, which is expected to improve workplace health and productivity.

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] The user opens the dedicated application and enters their concerns into a text box. For example, they might enter, "Recently, I've been feeling stressed about interpersonal relationships at work." This input is then passed to the next step.

[0623] Step 2:

[0624] The device receives the text data entered by the user, generates an HTTP POST request, and sends it to the server. This request contains the entered text in JSON format, for example:

[0625] json

[0626] {

[0627] "message": "Recently, I've been feeling stressed about relationships at work."

[0628] }

[0629] This request is passed to the server.

[0630] Step 3:

[0631] The server receives the HTTP POST request sent from the device. It extracts the user's input message from the request body and passes it to the emotion analysis engine. The server then sends the input data to the emotion analysis engine for analysis.

[0632] Step 4:

[0633] The emotion analysis engine analyzes the user's emotional state from the received input message. For example, the emotion analysis engine detects emotions such as "stress" or "anxiety." The analysis result is returned to the server in the following JSON format:

[0634] json

[0635] {

[0636] "emotion": "stress"

[0637] }

[0638] Step 5:

[0639] The server receives the emotion information obtained from the emotion analysis engine and passes it to the natural language processing engine. Specifically, it creates the following prompt to generate a prompt sentence and call the API.

[0640] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0641] This prompt is sent to a natural language processing engine.

[0642] Step 6:

[0643] The natural language processing engine analyzes the prompts and generates optimal advice based on the user's concerns and emotions. For example, it might generate advice such as, "To improve communication with your colleagues, it's important to set up regular opportunities for feedback and maintain open dialogue. Also, pay attention to your own stress management." This advice is then returned to the server.

[0644] Step 7:

[0645] The server receives advice from the natural language processing engine, converts it into JSON format, and sends it to the terminal as an HTTP response. For example, the following data is sent to the terminal:

[0646] json

[0647] {

[0648] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0649] }

[0650] Step 8:

[0651] The device receives the response from the server and displays the advice within the application. The user can confirm and put into practice this advice, thereby gaining concrete ways to deal with worries and stress in the workplace.

[0652] (Application example 2)

[0653] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0654] In today's workplace, improving employee mental health and motivation is an important issue. However, especially in factories, employees often work 24 hours a day, limiting the time they have to consult with their superiors or colleagues. It is also difficult to grasp the psychological burden of workplace relationships and work-related stress in real time and provide appropriate advice. Therefore, there is a need for a system that can quickly respond to employees' concerns and provide appropriate advice that takes their emotions into consideration.

[0655] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from an employee, means for passing the accepted input content to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice as voice. This makes it possible to grasp the employee's concerns in real time and provide appropriate advice that takes emotions into consideration.

[0656] An "employee" is a worker who works for a company or organization and is employed to carry out duties.

[0657] "Means for accepting input" refers to the interface or system for receiving concerns and questions from employees.

[0658] A "natural language processing engine" is a program that analyzes input text data and understands its meaning and intent.

[0659] "Means for providing answers" refers to the methods and devices used to communicate advice and answers generated by the natural language processing engine to employees.

[0660] "Voice-to-text conversion means" refers to any technology or device used to convert an employee's speech into digital text.

[0661] An "emotion analysis engine" is a program for identifying and analyzing emotions and psychological states from text data.

[0662] "Generative AI model" refers to an artificial intelligence model that generates appropriate advice based on input data.

[0663] "Voice output means" refers to a device or system that converts the generated text advice into voice and transmits it to employees.

[0664] A system for carrying out this invention provides prompt and appropriate advice to employees regarding mental worries and stress. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice by voice.

[0665] Server Processing

[0666] The server receives input data sent from the device and passes it to a sentiment analysis engine to extract emotional information. This sentiment analysis engine uses Azure Cognitive Services or similar. The server then queries a natural language processing engine along with the emotional information to generate appropriate advice. This generation uses a generative AI model such as OpenAI's GPT-3.

[0667] For example, if the server receives the input, "Recently, working late-night shifts has been tough and mentally stressful," the emotion analysis engine extracts "stress" as emotional information.The server then sends the following prompt sentence to the generative AI model:

[0668] Example prompt sentence:

[0669] A user is worried about 'lately working late-night shifts has been tough and mentally exhausting' and the emotion they are feeling is 'stress'. Please provide appropriate advice.

[0670] Terminal handling

[0671] The device receives voice input from employees and converts this speech into text using Google's speech recognition API, etc. It also receives the generated advice from the server and provides it to employees in audio format using Google Text-to-Speech, etc.

[0672] For example, if an employee makes a voice input such as "I've been feeling stressed about interpersonal relationships at work recently," the device converts this voice into text and sends it to the server. After receiving the generated advice from the server, the device converts the advice into voice and conveys it to the employee.

[0673] How users use it

[0674] Users talk about their concerns into a microphone built into the robot, and the system converts the speech into text and sends it to the server. The server uses emotion analysis and generative AI models to generate appropriate advice, which the device then relays to the user via voice. This process allows users to receive specific, emotionally appropriate advice in real time.

[0675] In this way, this system can consistently perform everything from voice input to emotion analysis, advice generation, and voice output, making it possible to respond quickly and appropriately to the various workplace worries and stresses that employees face.

[0676] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0677] Step 1:

[0678] The user inputs their concerns by voice. For example, they might say, "Recently, I've been feeling stressed about interpersonal relationships at work." The input is voice data.

[0679] Step 2:

[0680] The device receives voice data and converts it into text using Google's speech recognition API. Specifically, the voice data is sent to the speech recognition engine and text data is obtained. The output is text data.

[0681] Step 3:

[0682] The device sends text data to the server as an HTTP POST request. The request content includes the user's text input. The output is the text data sent to the server.

[0683] Step 4:

[0684] The server passes the received text data to a sentiment analysis engine (e.g., Azure Cognitive Services) to extract emotional information. The sentiment analysis engine identifies emotions (e.g., "stress" or "anxiety") from the text data. The output is emotional information.

[0685] Step 5:

[0686] The server passes the emotion information and text data to a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate advice. The generative AI model creates advice based on the given prompt. The output is the advice text data.

[0687] Step 6:

[0688] The server sends the generated advice to the terminal as an HTTP response. The response content includes the generated advice. The output is the text data of the advice sent to the terminal.

[0689] Step 7:

[0690] The device converts the received text data of advice into speech using the Google Text-to-Speech API. Specifically, the text data is sent to a speech synthesis engine, and speech data is obtained. The output is speech data.

[0691] Step 8:

[0692] The terminal provides the generated voice data to the user through a speaker, and the user receives the advice by voice. The output is the voice advice provided to the user.

[0693] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0694] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0695] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0696] [Third embodiment]

[0697] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0698] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0699] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0700] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0701] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0702] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0703] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0704] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0705] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0706] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0707] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0708] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0709] This invention is a system that provides advice 24 hours a day regarding workplace worries and personal problems that employees have, and contributes to the mental care and motivation of employees.

[0710] System Overview

[0711] The system includes a terminal for employees to input their concerns, a server that processes the concerns, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed by the natural language processing engine and appropriate advice is returned.

[0712] Program processing

[0713] User

[0714] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0715] Terminal

[0716] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format. The request is sent to a URL set on the server.

[0717] server

[0718] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's concerns.

[0719] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0720] server

[0721] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0722] Terminal

[0723] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0724] Specific examples

[0725] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0726] In this way, the system provides an effective means for quickly resolving employee concerns, improving workplace health and productivity.

[0727] The processing flow will be explained below.

[0728] Step 1:

[0729] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0730] Step 2:

[0731] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, like this:

[0732] json

[0733] {

[0734] "message": "Recently, I've been feeling stressed about relationships at work."

[0735] }

[0736] The terminal sends this request to the server.

[0737] Step 3:

[0738] The server receives the HTTP POST request and extracts the user input message from the request body.

[0739] Step 4:

[0740] The server sends the extracted message to the natural language processing engine. Specifically, it sends the message by calling the API as follows:

[0741] python

[0742] response = openai.Completion.create(

[0743] engine="davinci",

[0744] prompt=f"The user is having trouble with '{user_input}'. Please provide appropriate advice.",

[0745] max_tokens=150

[0746] )

[0747] Step 5:

[0748] A natural language processing engine analyzes the received message and generates appropriate advice, such as "To improve communication with colleagues, it is important to maintain open dialogue and increase opportunities for feedback."

[0749] Step 6:

[0750] The natural language processing engine returns the generated advice to the server.

[0751] Step 7:

[0752] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0753] json

[0754] {

[0755] "advice": "To improve communication with colleagues, it's important to foster open dialogue and increase opportunities for feedback."

[0756] }

[0757] Step 8:

[0758] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0759] Example 1

[0760] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0761] In today's workplaces, employees are increasingly experiencing stress and worries, creating a need for systems that can quickly and appropriately address these issues. Traditional methods of dealing with issues through dialogue with the HR department or superiors often result in delayed responses and require a certain amount of time for consultation, making it difficult to resolve issues efficiently. This can lead to problems with employee mental health and a decline in motivation.

[0762] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0763] In this invention, the server includes means for accepting input from employees, means for transmitting the accepted input content to the server, means for the server to pass the input content to a natural language processing engine and generate a prompt sentence, and means for the server to receive advice obtained from the natural language processing engine and provide it to the employee, thereby making it possible to quickly and effectively resolve the worries and stress of employees.

[0764] An "employee" is an individual employed by an organization or company to perform work.

[0765] "Input" refers to the act of an employee providing text or information to the system.

[0766] "Acceptance means" refers to the hardware and software used to collect and process employee input.

[0767] A "server" is a computer system on a network that processes data and runs programs.

[0768] A "natural language processing engine" is a program and algorithm for analyzing input linguistic data and generating appropriate responses.

[0769] A "prompt sentence" is a formatted text that provides instructions to a natural language processing engine.

[0770] "Advice" refers to advice or solutions provided to employees regarding their concerns or problems.

[0771] "Means for providing" refers to the hardware and software for displaying and communicating the advice generated by the server to employees.

[0772] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. The system includes a terminal where employees can input their concerns, a server that processes the concerns, and a natural language processing engine.

[0773] System Overview

[0774] 1. Users

[0775] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[0776] 2. Terminal

[0777] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format, and the destination URL is set on the server.

[0778] 3. Server

[0779] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's inputted problem.

[0780] 4. Natural Language Processing Engine

[0781] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[0782] 5. Server

[0783] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[0784] 6. Terminal

[0785] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[0786] Specific examples

[0787] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[0788] Prompt Sentence Examples

[0789] If an employee enters, "Recently, the pressure at work has increased and I feel stressed," the following prompt sentence is used as input to the generative AI model:

[0790] What specific advice would you give to employees who are feeling stressed due to increased pressure at work?

[0791]

[0792] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0793] Step 1:

[0794] The user inputs their concerns

[0795] The user (employee) opens the dedicated application and enters their concerns in a text box. For example, they might enter something like, "Recently, the pressure at work has increased and I feel stressed." The entered concerns are saved in the application's input field and are ready to be sent to the server.

[0796] Step 2:

[0797] The device sends input to the server

[0798] The device (PC or smartphone) reads the text of the problem entered by the user in the input field and sends it to the server as an HTTP POST request. The input data is converted to JSON format and included in the body of the HTTP request. The destination URL is the server's endpoint. The device outputs JSON format data, which the server receives as input.

[0799] Step 3:

[0800] The server receives and analyzes the message

[0801] The server receives an HTTP POST request sent from the terminal. It extracts the message from the body of the request and prepares to pass it to the natural language processing engine. At this time, the server checks the contents of the message to ensure that no data is missing. The server's input is the message in the body of the HTTP request, and its output is a prompt sentence to pass to the natural language processing engine.

[0802] Step 4:

[0803] The server makes an API call to the natural language processing engine.

[0804] The server generates a prompt sentence based on the received message and sends it to the API endpoint of the natural language processing engine. For example, the prompt sentence might be, "Please give some specific advice to an employee who is feeling stressed due to increasing pressure at work." The input to the server is the extracted message, and the output is the prompt sentence sent to the natural language processing engine.

[0805] Step 5:

[0806] Natural language processing engine generates advice

[0807] The natural language processing engine analyzes the received prompt sentence and generates appropriate advice using a knowledge base. For example, it generates advice such as, "If you are feeling pressure at work, we recommend that you first review your work priorities and focus on the most important tasks." The input to the natural language processing engine is the prompt sentence, and the output is the generated advice.

[0808] Step 6:

[0809] The server receives the advice and reformats it.

[0810] The server receives the advice generated by the natural language processing engine and converts it into JSON format. It prepares the converted data to be sent to the terminal as an HTTP response. The input of the server is the generated advice, and the output is the response data in JSON format.

[0811] Step 7:

[0812] The device receives and displays the advice

[0813] The terminal receives an HTTP response from the server and extracts the advice text data from the response body. The extracted advice is displayed in a specific display area within the application, allowing the user to obtain advice as a specific solution. The input of the terminal is the response received from the server, and the output is the advice to be displayed.

[0814] (Application example 1)

[0815] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0816] In today's workplace, mental health concerns and stress are on the rise among employees, requiring prompt and appropriate responses. However, with limited time and resources to consult with superiors or professional counselors, there is a lack of effective ways to resolve employees' concerns. To solve this problem, an automated system that can respond to employees' concerns 24 hours a day is needed.

[0817] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0818] In this invention, the server includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model, thereby enabling the employee's concern to be quickly analyzed and appropriate advice to be provided immediately.

[0819] "Means for accepting input from employees" refers to devices or software that provide an interface for employees to input their concerns or questions, and that have the function of accepting that input.

[0820] "Means for passing accepted input content to the natural language processing engine" refers to devices or software that have the function of converting the content entered by employees into an appropriate format and sending it to the natural language processing engine.

[0821] The "means for providing employees with answers obtained from the natural language processing engine" refers to a device or software that has the function of notifying employees of advice generated by the natural language processing engine.

[0822] "Means for using a generative AI model to analyze input concerns" refers to devices or software that have the function of utilizing a generative AI model to analyze concerns or consultation details input by employees.

[0823] "Means for creating and sending prompt sentences to a generative AI model" refers to devices or software that have the function of creating prompt sentences to request an appropriate analysis from a generative AI model and sending those prompt sentences to the model.

[0824] This invention is a system that provides 24-hour advice to employees regarding workplace concerns and personal problems. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model.

[0825] System configuration

[0826] 1. Accept employee input by:

[0827] Users use devices such as smartphones or computers to enter their concerns into a text box within a dedicated application. This application is built using React Native. For example, an employee might enter a concern such as, "Recently, I've been feeling more stressed due to work pressure."

[0828] 2. A way to pass the received input to the natural language processing engine:

[0829] The terminal wraps the input content in JSON format and sends it to the server as an HTTP POST request, which is received by a server built using Node.js and Express.

[0830] 3. How to provide answers from the natural language processing engine to employees:

[0831] The server analyzes the received request and forwards the input to OpenAI's GPT-4 API. The generative AI model receives a prompt (e.g., "Please provide advice for the following problem: I've recently been feeling more stressed due to work pressure") and generates appropriate advice.

[0832] 4. How to use generative AI models to analyze input concerns:

[0833] The generative AI model analyzes the problem and generates appropriate advice, such as "To reduce work pressure, it is effective to take regular breaks and focus on important tasks."

[0834] 5. How to create and send prompts to a generative AI model:

[0835] The server creates a prompt and sends it to the OpenAI GPT-4 API. The generated advice is returned to the server in JSON format, and the server then forwards it to the device.

[0836] Specific examples

[0837] Consider the case where an employee inputs a concern into this system: "Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." In this case, the device sends the message to the server, which passes it on to the natural language processing engine. The natural language processing engine generates advice based on the prompt: "Please provide advice for the following concern: Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." The final advice generated and provided to the employee is: "To improve communication with colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue."

[0838] This system is expected to improve workplace health and productivity by allowing employees to receive prompt and appropriate advice anytime, anywhere.

[0839] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0840] Step 1:

[0841] The user opens a dedicated application on their smartphone or computer and enters their concerns into a text box. For example, the input data might be, "Recently, the pressure at work has increased and I feel stressed." This text data is entered into the device, and the device is ready to proceed to the next step.

[0842] Step 2:

[0843] The device wraps the input text data in JSON format as an HTTP POST request and sends it to the server. The input of this request is the employee's concerns, and the output is the data sent via communication to the server. Specifically, the device sends a request to the API endpoint.

[0844] Step 3:

[0845] The server receives an HTTP POST request sent from the device and extracts the input message from the request body. The input is the text data of the problem received in JSON format, and the output is the extracted message. Specifically, the server analyzes the received data and stores the message in the appropriate variable.

[0846] Step 4:

[0847] The server creates a prompt from the extracted text message to be passed to the generative AI model, specifically the OpenAI GPT-4 API, and sends an API request. The input is the text data of the employee's concerns, and the output is the generated prompt and the result of sending the API request. Specifically, the server incorporates the content of the concerns into the prompt and sends it to the GPT-4 API.

[0848] Step 5:

[0849] The generative AI model (GPT-4) analyzes the received prompt and generates appropriate advice. The input is the prompt sent from the server, and the output is the generated advice text. Specifically, the generative AI model performs natural language processing to derive the optimal advice.

[0850] Step 6:

[0851] The server receives the advice obtained from the generative AI model, converts it to JSON format, and sends it to the terminal as an HTTP response. The input is the text of the advice from the generative AI model, and the output is the data to be sent to the terminal. Specifically, the server wraps the advice in JSON format and sends it back to the terminal.

[0852] Step 7:

[0853] The terminal displays the received advice within the application. The input is the JSON data of the advice received from the server, and the output is the advice displayed in a form that the user can visually confirm. Specifically, the terminal analyzes the received data and displays the advice in the user interface.

[0854] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0855] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. In particular, by combining it with an emotion engine, it is possible to recognize employees' emotional states and provide more appropriate advice.

[0856] System Overview

[0857] The system includes a terminal for employees to input their concerns, a server that processes the concerns, an emotion engine, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed through the emotion engine and the natural language processing engine, and appropriate advice is returned.

[0858] Program processing

[0859] User

[0860] Employees open a dedicated application and enter their concerns. For example, they can write, "Recently, I've been feeling stressed about interpersonal relationships at work" in the text box.

[0861] Terminal

[0862] The device (employee's PC or smartphone) receives the inputted concern. Then, it generates an HTTP POST request and sends it to the server. This request contains the user's input in JSON format as shown below.

[0863] json

[0864] {

[0865] "message": "Recently, I've been feeling stressed about relationships at work."

[0866] }

[0867] server

[0868] The server receives the HTTP POST request sent from the terminal and extracts the user's input message from the request body.

[0869] The server first passes the extracted message to an emotion engine, which analyzes the user's emotional state. For example, the emotion engine detects emotions such as "stress" or "anxiety" from the input message.

[0870] Next, the server passes the emotion information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotion information.

[0871] python

[0872] response = openai.Completion.create(

[0873] engine="davinci",

[0874] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0875] max_tokens=150

[0876] )

[0877] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0878] The server receives the generated advice, converts it into JSON format, and sends it to the terminal as an HTTP response.

[0879] json

[0880] {

[0881] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0882] }

[0883] Terminal

[0884] The device receives the response from the server and displays the advice within the application, which the user can then confirm and implement.

[0885] Specific examples

[0886] For example, suppose an employee inputs into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion engine to recognize emotions such as "irritation" or "anxiety." The natural language processing engine then generates advice incorporating the emotional information, which is returned to the device via the server. Ultimately, the system provides the employee with the following advice: "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0887] In this way, by combining this system with an emotion engine, it is possible to gain a deeper understanding of employees' concerns and provide more appropriate advice, thereby contributing to improving workplace health and productivity.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[0891] Step 2:

[0892] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, as follows:

[0893] json

[0894] {

[0895] "message": "Recently, I've been feeling stressed about relationships at work."

[0896] }

[0897] The terminal sends this request to the server.

[0898] Step 3:

[0899] The server receives the HTTP POST request and extracts the user input message from the request body.

[0900] Step 4:

[0901] The server passes the extracted message to the emotion engine, which analyzes the user's emotional state. For example, the emotion engine can detect emotions such as "stress" or "anxiety" from the input message.

[0902] Step 5:

[0903] The emotion engine returns the analyzed emotion information to the server. For example, it returns information such as "The user's emotion is stress."

[0904] Step 6:

[0905] The server passes the emotional information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotional information.

[0906] python

[0907] response = openai.Completion.create(

[0908] engine="davinci",

[0909] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[0910] max_tokens=150

[0911] )

[0912] For example, the prompt may read, "The user is worried about 'Recently, I've been feeling stressed by interpersonal relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0913] Step 7:

[0914] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0915] Step 8:

[0916] The natural language processing engine returns the generated advice to the server.

[0917] Step 9:

[0918] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[0919] json

[0920] {

[0921] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0922] }

[0923] Step 10:

[0924] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[0925] Example 2

[0926] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0927] Previous systems lacked support for dealing with workplace worries and personal problems, and it was particularly difficult to take emotional factors into account. This made it difficult to provide appropriate advice quickly, creating challenges for employees' mental health and motivation. Furthermore, in many cases, it took time to consult with superiors, resulting in a decline in productivity.

[0928] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0929] In this invention, the server includes a means for accepting input from employees, a means for passing the accepted input to an emotion analysis engine, a means for passing emotional information obtained from the emotion analysis engine to a natural language processing engine, and a means for providing the employee with a response obtained from the natural language processing engine. This makes it possible to appropriately analyze the emotional state of employees and quickly provide specific advice based on that analysis. It also reduces the time spent consulting with superiors, contributing to the mental health of employees and improving their motivation.

[0930] "Means for accepting input from employees" refers to a function that provides an interface that allows employees to input their concerns and problems in text format using a dedicated application.

[0931] The "means of passing accepted input content to the emotion analysis engine" is a function that converts text data entered by employees into an appropriate format and sends it to the emotion analysis engine.

[0932] An "emotion analysis engine" is a software module that analyzes a user's emotional state from input text, identifying emotions such as "stress" or "anxiety," for example.

[0933] The "means for passing emotional information obtained from the emotion analysis engine to the natural language processing engine" is a function for receiving emotional information output from the emotion analysis engine and passing it to the natural language processing engine.

[0934] A "natural language processing engine" is a software module that generates appropriate advice based on emotional information and input concerns.

[0935] The "means for providing employees with answers obtained from the natural language processing engine" is a function for displaying advice generated from the natural language processing engine to employees.

[0936] The "system" refers to a comprehensive configuration that includes the device where employees input data, the server, the emotion analysis engine, the natural language processing engine, and the software and hardware that connects them.

[0937] "Means for identifying that the input content is a problem or consultation" is a function for automatically determining whether the text entered by an employee is a problem or consultation.

[0938] "Measures aimed at reducing the time spent consulting with superiors" are ideas and techniques that reduce the time employees spend directly consulting with superiors and enable efficient problem-solving.

[0939] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems. By combining an emotion analysis engine and a natural language processing engine, this system is able to recognize employees' emotional states and provide more appropriate advice.

[0940] System configuration

[0941] The system includes a terminal for employees to input their concerns, a server for processing the concerns, a sentiment analysis engine, and a natural language processing engine.

[0942] Terminal

[0943] The devices are PCs or smartphones used by employees. Employees open a dedicated application and input their concerns or problems. This input is sent to the server as an HTTP POST request.

[0944] server

[0945] The server receives the HTTP POST request sent from the device and extracts the user's input message from the request body. It then passes this message to an emotion analysis engine to analyze the user's emotional state. The emotion analysis engine detects emotions such as "stress" and "anxiety" from the input message.

[0946] The emotion information obtained from the emotion analysis engine is passed to the natural language processing engine. The server uses OpenAI's API to generate prompts as follows:

[0947] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0948] The natural language processing engine generates optimal advice based on the prompts and sends it back to the server, which converts the advice into JSON format and sends it to the device as an HTTP response.

[0949] Sentiment Analysis Engine

[0950] The sentiment analysis engine includes an algorithm for analyzing input text data and identifying the emotional state of the user. The algorithm uses natural language processing techniques to identify the emotional state.

[0951] Natural Language Processing Engine

[0952] The natural language processing engine is a software module that generates appropriate advice based on the emotional information obtained from the emotion analysis engine and the user's concerns. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-3).

[0953] Specific examples

[0954] For example, an employee might input into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion analysis engine to recognize emotions such as "irritation" or "anxiety." The server then uses a natural language processing engine to generate advice that incorporates the emotional information. The generated advice is sent back to the device via the server and provided to the employee in the form of, "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[0955] This system allows employees to receive appropriate advice at any time, reducing the amount of time they spend consulting with their superiors and improving their mental health, which is expected to improve workplace health and productivity.

[0956] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0957] Step 1:

[0958] The user opens the dedicated application and enters their concerns into a text box. For example, they might enter, "Recently, I've been feeling stressed about interpersonal relationships at work." This input is then passed to the next step.

[0959] Step 2:

[0960] The device receives the text data entered by the user, generates an HTTP POST request, and sends it to the server. This request contains the entered text in JSON format, for example:

[0961] json

[0962] {

[0963] "message": "Recently, I've been feeling stressed about relationships at work."

[0964] }

[0965] This request is passed to the server.

[0966] Step 3:

[0967] The server receives the HTTP POST request sent from the device. It extracts the user's input message from the request body and passes it to the emotion analysis engine. The server then sends the input data to the emotion analysis engine for analysis.

[0968] Step 4:

[0969] The emotion analysis engine analyzes the user's emotional state from the received input message. For example, the emotion analysis engine detects emotions such as "stress" or "anxiety." The analysis result is returned to the server in the following JSON format:

[0970] json

[0971] {

[0972] "emotion": "stress"

[0973] }

[0974] Step 5:

[0975] The server receives the emotion information obtained from the emotion analysis engine and passes it to the natural language processing engine. Specifically, it creates the following prompt to generate a prompt sentence and call the API.

[0976] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[0977] This prompt is sent to a natural language processing engine.

[0978] Step 6:

[0979] The natural language processing engine analyzes the prompts and generates optimal advice based on the user's concerns and emotions. For example, it might generate advice such as, "To improve communication with your colleagues, it's important to set up regular opportunities for feedback and maintain open dialogue. Also, pay attention to your own stress management." This advice is then returned to the server.

[0980] Step 7:

[0981] The server receives advice from the natural language processing engine, converts it into JSON format, and sends it to the terminal as an HTTP response. For example, the following data is sent to the terminal:

[0982] json

[0983] {

[0984] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[0985] }

[0986] Step 8:

[0987] The device receives the response from the server and displays the advice within the application. The user can confirm and put into practice this advice, thereby gaining concrete ways to deal with worries and stress in the workplace.

[0988] (Application example 2)

[0989] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0990] In today's workplace, improving employee mental health and motivation is an important issue. However, especially in factories, employees often work 24 hours a day, limiting the time they have to consult with their superiors or colleagues. It is also difficult to grasp the psychological burden of workplace relationships and work-related stress in real time and provide appropriate advice. Therefore, there is a need for a system that can quickly respond to employees' concerns and provide appropriate advice that takes their emotions into consideration.

[0991] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from an employee, means for passing the accepted input content to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice as voice. This makes it possible to grasp the employee's concerns in real time and provide appropriate advice that takes emotions into consideration.

[0992] An "employee" is a worker who works for a company or organization and is employed to carry out duties.

[0993] "Means for accepting input" refers to the interface or system for receiving concerns and questions from employees.

[0994] A "natural language processing engine" is a program that analyzes input text data and understands its meaning and intent.

[0995] "Means for providing answers" refers to the methods and devices used to communicate advice and answers generated by the natural language processing engine to employees.

[0996] "Voice-to-text conversion means" refers to any technology or device used to convert an employee's speech into digital text.

[0997] An "emotion analysis engine" is a program for identifying and analyzing emotions and psychological states from text data.

[0998] "Generative AI model" refers to an artificial intelligence model that generates appropriate advice based on input data.

[0999] "Voice output means" refers to a device or system that converts the generated text advice into voice and transmits it to employees.

[1000] A system for carrying out this invention provides prompt and appropriate advice to employees regarding mental worries and stress. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice by voice.

[1001] Server Processing

[1002] The server receives input data sent from the device and passes it to a sentiment analysis engine to extract emotional information. This sentiment analysis engine uses Azure Cognitive Services or similar. The server then queries a natural language processing engine along with the emotional information to generate appropriate advice. This generation uses a generative AI model such as OpenAI's GPT-3.

[1003] For example, if the server receives the input, "Recently, working late-night shifts has been tough and mentally stressful," the emotion analysis engine extracts "stress" as emotional information.The server then sends the following prompt sentence to the generative AI model:

[1004] Example prompt sentence:

[1005] A user is worried about 'lately working late-night shifts has been tough and mentally exhausting' and the emotion they are feeling is 'stress'. Please provide appropriate advice.

[1006] Terminal handling

[1007] The device receives voice input from employees and converts this speech into text using Google's speech recognition API, etc. It also receives the generated advice from the server and provides it to employees in audio format using Google Text-to-Speech, etc.

[1008] For example, if an employee makes a voice input such as "I've been feeling stressed about interpersonal relationships at work recently," the device converts this voice into text and sends it to the server. After receiving the generated advice from the server, the device converts the advice into voice and conveys it to the employee.

[1009] How users use it

[1010] Users talk about their concerns into a microphone built into the robot, and the system converts the speech into text and sends it to the server. The server uses emotion analysis and generative AI models to generate appropriate advice, which the device then relays to the user via voice. This process allows users to receive specific, emotionally appropriate advice in real time.

[1011] In this way, this system can consistently perform everything from voice input to emotion analysis, advice generation, and voice output, making it possible to respond quickly and appropriately to the various workplace worries and stresses that employees face.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Step 1:

[1014] The user inputs their concerns by voice. For example, they might say, "Recently, I've been feeling stressed about interpersonal relationships at work." The input is voice data.

[1015] Step 2:

[1016] The device receives voice data and converts it into text using Google's speech recognition API. Specifically, the voice data is sent to the speech recognition engine and text data is obtained. The output is text data.

[1017] Step 3:

[1018] The device sends text data to the server as an HTTP POST request. The request content includes the user's text input. The output is the text data sent to the server.

[1019] Step 4:

[1020] The server passes the received text data to a sentiment analysis engine (e.g., Azure Cognitive Services) to extract emotional information. The sentiment analysis engine identifies emotions (e.g., "stress" or "anxiety") from the text data. The output is emotional information.

[1021] Step 5:

[1022] The server passes the emotion information and text data to a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate advice. The generative AI model creates advice based on the given prompt. The output is the advice text data.

[1023] Step 6:

[1024] The server sends the generated advice to the terminal as an HTTP response. The response content includes the generated advice. The output is the text data of the advice sent to the terminal.

[1025] Step 7:

[1026] The device converts the received text data of advice into speech using the Google Text-to-Speech API. Specifically, the text data is sent to a speech synthesis engine, and speech data is obtained. The output is speech data.

[1027] Step 8:

[1028] The terminal provides the generated voice data to the user through a speaker, and the user receives the advice by voice. The output is the voice advice provided to the user.

[1029] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1030] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1031] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1032] [Fourth embodiment]

[1033] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1034] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1035] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1036] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1037] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1038] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1039] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1040] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1041] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1042] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1043] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1044] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1045] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1046] This invention is a system that provides advice 24 hours a day regarding workplace worries and personal problems that employees have, and contributes to the mental care and motivation of employees.

[1047] System Overview

[1048] The system includes a terminal for employees to input their concerns, a server that processes the concerns, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed by the natural language processing engine and appropriate advice is returned.

[1049] Program processing

[1050] User

[1051] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[1052] Terminal

[1053] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format. The request is sent to a URL set on the server.

[1054] server

[1055] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's concerns.

[1056] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[1057] server

[1058] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[1059] Terminal

[1060] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[1061] Specific examples

[1062] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[1063] In this way, the system provides an effective means for quickly resolving employee concerns, improving workplace health and productivity.

[1064] The processing flow will be explained below.

[1065] Step 1:

[1066] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[1067] Step 2:

[1068] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, like this:

[1069] json

[1070] {

[1071] "message": "Recently, I've been feeling stressed about relationships at work."

[1072] }

[1073] The terminal sends this request to the server.

[1074] Step 3:

[1075] The server receives the HTTP POST request and extracts the user input message from the request body.

[1076] Step 4:

[1077] The server sends the extracted message to the natural language processing engine. Specifically, it sends the message by calling the API as follows:

[1078] python

[1079] response = openai.Completion.create(

[1080] engine="davinci",

[1081] prompt=f"The user is having trouble with '{user_input}'. Please provide appropriate advice.",

[1082] max_tokens=150

[1083] )

[1084] Step 5:

[1085] A natural language processing engine analyzes the received message and generates appropriate advice, such as "To improve communication with colleagues, it is important to maintain open dialogue and increase opportunities for feedback."

[1086] Step 6:

[1087] The natural language processing engine returns the generated advice to the server.

[1088] Step 7:

[1089] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[1090] json

[1091] {

[1092] "advice": "To improve communication with colleagues, it's important to foster open dialogue and increase opportunities for feedback."

[1093] }

[1094] Step 8:

[1095] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[1096] Example 1

[1097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1098] In today's workplaces, employees are increasingly experiencing stress and worries, creating a need for systems that can quickly and appropriately address these issues. Traditional methods of dealing with issues through dialogue with the HR department or superiors often result in delayed responses and require a certain amount of time for consultation, making it difficult to resolve issues efficiently. This can lead to problems with employee mental health and a decline in motivation.

[1099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1100] In this invention, the server includes means for accepting input from employees, means for transmitting the accepted input content to the server, means for the server to pass the input content to a natural language processing engine and generate a prompt sentence, and means for the server to receive advice obtained from the natural language processing engine and provide it to the employee, thereby making it possible to quickly and effectively resolve the worries and stress of employees.

[1101] An "employee" is an individual employed by an organization or company to perform work.

[1102] "Input" refers to the act of an employee providing text or information to the system.

[1103] "Acceptance means" refers to the hardware and software used to collect and process employee input.

[1104] A "server" is a computer system on a network that processes data and runs programs.

[1105] A "natural language processing engine" is a program and algorithm for analyzing input linguistic data and generating appropriate responses.

[1106] A "prompt sentence" is a formatted text that provides instructions to a natural language processing engine.

[1107] "Advice" refers to advice or solutions provided to employees regarding their concerns or problems.

[1108] "Means for providing" refers to the hardware and software for displaying and communicating the advice generated by the server to employees.

[1109] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. The system includes a terminal where employees can input their concerns, a server that processes the concerns, and a natural language processing engine.

[1110] System Overview

[1111] 1. Users

[1112] When an employee has a problem, they open a dedicated application and enter their problem in a text box, for example, "Recently, the pressure at work has increased and I'm feeling stressed."

[1113] 2. Terminal

[1114] The device (user's PC or smartphone) creates an HTTP POST request to send the inputted concern to the server. This request contains the input message in JSON format, and the destination URL is set on the server.

[1115] 3. Server

[1116] The server receives the HTTP POST request sent from the device. It extracts the input message from the request body and passes it to the natural language processing engine. The server then makes an API call to the natural language processing engine, which generates advice appropriate to the employee's inputted problem.

[1117] 4. Natural Language Processing Engine

[1118] The natural language processing engine analyzes employees' concerns and generates appropriate advice from a related knowledge base. For example, it might say, "If you are feeling pressured at work, we recommend that you first re-prioritize your work and focus on the most important tasks."

[1119] 5. Server

[1120] When the server receives the generated advice, it converts it into JSON format and sends it to the terminal as an HTTP response.

[1121] 6. Terminal

[1122] The device will then display the received advice within the application, allowing employees to receive specific advice on the problem.

[1123] Specific examples

[1124] For example, suppose an employee inputs into the system a concern such as, "Recently, my relationships with coworkers have been strained, making it difficult for me to concentrate on my work." In this case, the device sends the message to the server, which then queries the natural language processing engine. The natural language processing engine generates advice for improving relationships at work and returns it to the device via the server. Ultimately, the employee is provided with advice such as, "To improve communication with colleagues, it is important to create regular opportunities for feedback and strive for open dialogue."

[1125] Prompt Sentence Examples

[1126] If an employee enters, "Recently, the pressure at work has increased and I feel stressed," the following prompt sentence is used as input to the generative AI model:

[1127] What specific advice would you give to employees who are feeling stressed due to increased pressure at work?

[1128]

[1129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1130] Step 1:

[1131] The user inputs their concerns

[1132] The user (employee) opens the dedicated application and enters their concerns in a text box. For example, they might enter something like, "Recently, the pressure at work has increased and I feel stressed." The entered concerns are saved in the application's input field and are ready to be sent to the server.

[1133] Step 2:

[1134] The device sends input to the server

[1135] The device (PC or smartphone) reads the text of the problem entered by the user in the input field and sends it to the server as an HTTP POST request. The input data is converted to JSON format and included in the body of the HTTP request. The destination URL is the server's endpoint. The device outputs JSON format data, which the server receives as input.

[1136] Step 3:

[1137] The server receives and analyzes the message

[1138] The server receives an HTTP POST request sent from the terminal. It extracts the message from the body of the request and prepares to pass it to the natural language processing engine. At this time, the server checks the contents of the message to ensure that no data is missing. The server's input is the message in the body of the HTTP request, and its output is a prompt sentence to pass to the natural language processing engine.

[1139] Step 4:

[1140] The server makes an API call to the natural language processing engine.

[1141] The server generates a prompt sentence based on the received message and sends it to the API endpoint of the natural language processing engine. For example, the prompt sentence might be, "Please give some specific advice to an employee who is feeling stressed due to increasing pressure at work." The input to the server is the extracted message, and the output is the prompt sentence sent to the natural language processing engine.

[1142] Step 5:

[1143] Natural language processing engine generates advice

[1144] The natural language processing engine analyzes the received prompt sentence and generates appropriate advice using a knowledge base. For example, it generates advice such as, "If you are feeling pressure at work, we recommend that you first review your work priorities and focus on the most important tasks." The input to the natural language processing engine is the prompt sentence, and the output is the generated advice.

[1145] Step 6:

[1146] The server receives the advice and reformats it.

[1147] The server receives the advice generated by the natural language processing engine and converts it into JSON format. It prepares the converted data to be sent to the terminal as an HTTP response. The input of the server is the generated advice, and the output is the response data in JSON format.

[1148] Step 7:

[1149] The device receives and displays the advice

[1150] The terminal receives an HTTP response from the server and extracts the advice text data from the response body. The extracted advice is displayed in a specific display area within the application, allowing the user to obtain advice as a specific solution. The input of the terminal is the response received from the server, and the output is the advice to be displayed.

[1151] (Application example 1)

[1152] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1153] In today's workplace, mental health concerns and stress are on the rise among employees, requiring prompt and appropriate responses. However, with limited time and resources to consult with superiors or professional counselors, there is a lack of effective ways to resolve employees' concerns. To solve this problem, an automated system that can respond to employees' concerns 24 hours a day is needed.

[1154] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1155] In this invention, the server includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model, thereby enabling the employee's concern to be quickly analyzed and appropriate advice to be provided immediately.

[1156] "Means for accepting input from employees" refers to devices or software that provide an interface for employees to input their concerns or questions, and that have the function of accepting that input.

[1157] "Means for passing accepted input content to the natural language processing engine" refers to devices or software that have the function of converting the content entered by employees into an appropriate format and sending it to the natural language processing engine.

[1158] The "means for providing employees with answers obtained from the natural language processing engine" refers to a device or software that has the function of notifying employees of advice generated by the natural language processing engine.

[1159] "Means for using a generative AI model to analyze input concerns" refers to devices or software that have the function of utilizing a generative AI model to analyze concerns or consultation details input by employees.

[1160] "Means for creating and sending prompt sentences to a generative AI model" refers to devices or software that have the function of creating prompt sentences to request an appropriate analysis from a generative AI model and sending those prompt sentences to the model.

[1161] This invention is a system that provides 24-hour advice to employees regarding workplace concerns and personal problems. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with an answer obtained from the natural language processing engine, means for using a generative AI model to analyze the input concern, and means for creating and sending a prompt sentence to the generative AI model.

[1162] System configuration

[1163] 1. Accept employee input by:

[1164] Users use devices such as smartphones or computers to enter their concerns into a text box within a dedicated application. This application is built using React Native. For example, an employee might enter a concern such as, "Recently, I've been feeling more stressed due to work pressure."

[1165] 2. A way to pass the received input to the natural language processing engine:

[1166] The terminal wraps the input content in JSON format and sends it to the server as an HTTP POST request, which is received by a server built using Node.js and Express.

[1167] 3. How to provide answers from the natural language processing engine to employees:

[1168] The server analyzes the received request and forwards the input to OpenAI's GPT-4 API. The generative AI model receives a prompt (e.g., "Please provide advice for the following problem: I've recently been feeling more stressed due to work pressure") and generates appropriate advice.

[1169] 4. How to use generative AI models to analyze input concerns:

[1170] The generative AI model analyzes the problem and generates appropriate advice, such as "To reduce work pressure, it is effective to take regular breaks and focus on important tasks."

[1171] 5. How to create and send prompts to a generative AI model:

[1172] The server creates a prompt and sends it to the OpenAI GPT-4 API. The generated advice is returned to the server in JSON format, and the server then forwards it to the device.

[1173] Specific examples

[1174] Consider the case where an employee inputs a concern into this system: "Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." In this case, the device sends the message to the server, which passes it on to the natural language processing engine. The natural language processing engine generates advice based on the prompt: "Please provide advice for the following concern: Recently, my relationships with coworkers have been strained, and I can't concentrate on my work." The final advice generated and provided to the employee is: "To improve communication with colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue."

[1175] This system is expected to improve workplace health and productivity by allowing employees to receive prompt and appropriate advice anytime, anywhere.

[1176] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1177] Step 1:

[1178] The user opens a dedicated application on their smartphone or computer and enters their concerns into a text box. For example, the input data might be, "Recently, the pressure at work has increased and I feel stressed." This text data is entered into the device, and the device is ready to proceed to the next step.

[1179] Step 2:

[1180] The device wraps the input text data in JSON format as an HTTP POST request and sends it to the server. The input of this request is the employee's concerns, and the output is the data sent via communication to the server. Specifically, the device sends a request to the API endpoint.

[1181] Step 3:

[1182] The server receives an HTTP POST request sent from the device and extracts the input message from the request body. The input is the text data of the problem received in JSON format, and the output is the extracted message. Specifically, the server analyzes the received data and stores the message in the appropriate variable.

[1183] Step 4:

[1184] The server creates a prompt from the extracted text message to be passed to the generative AI model, specifically the OpenAI GPT-4 API, and sends an API request. The input is the text data of the employee's concerns, and the output is the generated prompt and the result of sending the API request. Specifically, the server incorporates the content of the concerns into the prompt and sends it to the GPT-4 API.

[1185] Step 5:

[1186] The generative AI model (GPT-4) analyzes the received prompt and generates appropriate advice. The input is the prompt sent from the server, and the output is the generated advice text. Specifically, the generative AI model performs natural language processing to derive the optimal advice.

[1187] Step 6:

[1188] The server receives the advice obtained from the generative AI model, converts it to JSON format, and sends it to the terminal as an HTTP response. The input is the text of the advice from the generative AI model, and the output is the data to be sent to the terminal. Specifically, the server wraps the advice in JSON format and sends it back to the terminal.

[1189] Step 7:

[1190] The terminal displays the received advice within the application. The input is the JSON data of the advice received from the server, and the output is the advice displayed in a form that the user can visually confirm. Specifically, the terminal analyzes the received data and displays the advice in the user interface.

[1191] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1192] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems, contributing to the mental health and motivation of employees. In particular, by combining it with an emotion engine, it is possible to recognize employees' emotional states and provide more appropriate advice.

[1193] System Overview

[1194] The system includes a terminal for employees to input their concerns, a server that processes the concerns, an emotion engine, and a natural language processing engine. When an employee inputs their concerns, the information is analyzed through the emotion engine and the natural language processing engine, and appropriate advice is returned.

[1195] Program processing

[1196] User

[1197] Employees open a dedicated application and enter their concerns. For example, they can write, "Recently, I've been feeling stressed about interpersonal relationships at work" in the text box.

[1198] Terminal

[1199] The device (employee's PC or smartphone) receives the inputted concern. Then, it generates an HTTP POST request and sends it to the server. This request contains the user's input in JSON format as shown below.

[1200] json

[1201] {

[1202] "message": "Recently, I've been feeling stressed about relationships at work."

[1203] }

[1204] server

[1205] The server receives the HTTP POST request sent from the terminal and extracts the user's input message from the request body.

[1206] The server first passes the extracted message to an emotion engine, which analyzes the user's emotional state. For example, the emotion engine detects emotions such as "stress" or "anxiety" from the input message.

[1207] Next, the server passes the emotion information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotion information.

[1208] python

[1209] response = openai.Completion.create(

[1210] engine="davinci",

[1211] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[1212] max_tokens=150

[1213] )

[1214] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[1215] The server receives the generated advice, converts it into JSON format, and sends it to the terminal as an HTTP response.

[1216] json

[1217] {

[1218] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[1219] }

[1220] Terminal

[1221] The device receives the response from the server and displays the advice within the application, which the user can then confirm and implement.

[1222] Specific examples

[1223] For example, suppose an employee inputs into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion engine to recognize emotions such as "irritation" or "anxiety." The natural language processing engine then generates advice incorporating the emotional information, which is returned to the device via the server. Ultimately, the system provides the employee with the following advice: "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[1224] In this way, by combining this system with an emotion engine, it is possible to gain a deeper understanding of employees' concerns and provide more appropriate advice, thereby contributing to improving workplace health and productivity.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] The user opens the dedicated application and inputs their concerns. For example, they might type, "Recently, I've been feeling stressed about interpersonal relationships at work" into the text box.

[1228] Step 2:

[1229] The device receives the input and generates an HTTP POST request, which contains the user's input in JSON format, as follows:

[1230] json

[1231] {

[1232] "message": "Recently, I've been feeling stressed about relationships at work."

[1233] }

[1234] The terminal sends this request to the server.

[1235] Step 3:

[1236] The server receives the HTTP POST request and extracts the user input message from the request body.

[1237] Step 4:

[1238] The server passes the extracted message to the emotion engine, which analyzes the user's emotional state. For example, the emotion engine can detect emotions such as "stress" or "anxiety" from the input message.

[1239] Step 5:

[1240] The emotion engine returns the analyzed emotion information to the server. For example, it returns information such as "The user's emotion is stress."

[1241] Step 6:

[1242] The server passes the emotional information obtained from the emotion engine to the natural language processing engine. Specifically, it calls the API as follows to send the message and emotional information.

[1243] python

[1244] response = openai.Completion.create(

[1245] engine="davinci",

[1246] prompt=f"The user is worried about '{user_input}' and their emotion is '{emotion}'. Please provide appropriate advice.",

[1247] max_tokens=150

[1248] )

[1249] For example, the prompt may read, "The user is worried about 'Recently, I've been feeling stressed by interpersonal relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[1250] Step 7:

[1251] The natural language processing engine takes into account the user's concerns and emotional information to generate optimal advice, such as, "To improve communication with your colleagues, it's important to maintain open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[1252] Step 8:

[1253] The natural language processing engine returns the generated advice to the server.

[1254] Step 9:

[1255] The server converts the received advice into JSON format and sends it to the terminal as an HTTP response.

[1256] json

[1257] {

[1258] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[1259] }

[1260] Step 10:

[1261] The device receives the response from the server and displays the advice within the application, which the user can then review and implement.

[1262] Example 2

[1263] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1264] Previous systems lacked support for dealing with workplace worries and personal problems, and it was particularly difficult to take emotional factors into account. This made it difficult to provide appropriate advice quickly, creating challenges for employees' mental health and motivation. Furthermore, in many cases, it took time to consult with superiors, resulting in a decline in productivity.

[1265] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1266] In this invention, the server includes a means for accepting input from employees, a means for passing the accepted input to an emotion analysis engine, a means for passing emotional information obtained from the emotion analysis engine to a natural language processing engine, and a means for providing the employee with a response obtained from the natural language processing engine. This makes it possible to appropriately analyze the emotional state of employees and quickly provide specific advice based on that analysis. It also reduces the time spent consulting with superiors, contributing to the mental health of employees and improving their motivation.

[1267] "Means for accepting input from employees" refers to a function that provides an interface that allows employees to input their concerns and problems in text format using a dedicated application.

[1268] The "means of passing accepted input content to the emotion analysis engine" is a function that converts text data entered by employees into an appropriate format and sends it to the emotion analysis engine.

[1269] An "emotion analysis engine" is a software module that analyzes a user's emotional state from input text, identifying emotions such as "stress" or "anxiety," for example.

[1270] The "means for passing emotional information obtained from the emotion analysis engine to the natural language processing engine" is a function for receiving emotional information output from the emotion analysis engine and passing it to the natural language processing engine.

[1271] A "natural language processing engine" is a software module that generates appropriate advice based on emotional information and input concerns.

[1272] The "means for providing employees with answers obtained from the natural language processing engine" is a function for displaying advice generated from the natural language processing engine to employees.

[1273] The "system" refers to a comprehensive configuration that includes the device where employees input data, the server, the emotion analysis engine, the natural language processing engine, and the software and hardware that connects them.

[1274] "Means for identifying that the input content is a problem or consultation" is a function for automatically determining whether the text entered by an employee is a problem or consultation.

[1275] "Measures aimed at reducing the time spent consulting with superiors" are ideas and techniques that reduce the time employees spend directly consulting with superiors and enable efficient problem-solving.

[1276] This invention is a system that provides advice 24 hours a day to employees regarding workplace and personal problems. By combining an emotion analysis engine and a natural language processing engine, this system is able to recognize employees' emotional states and provide more appropriate advice.

[1277] System configuration

[1278] The system includes a terminal for employees to input their concerns, a server for processing the concerns, a sentiment analysis engine, and a natural language processing engine.

[1279] Terminal

[1280] The devices are PCs or smartphones used by employees. Employees open a dedicated application and input their concerns or problems. This input is sent to the server as an HTTP POST request.

[1281] server

[1282] The server receives the HTTP POST request sent from the device and extracts the user's input message from the request body. It then passes this message to an emotion analysis engine to analyze the user's emotional state. The emotion analysis engine detects emotions such as "stress" and "anxiety" from the input message.

[1283] The emotion information obtained from the emotion analysis engine is passed to the natural language processing engine. The server uses OpenAI's API to generate prompts as follows:

[1284] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[1285] The natural language processing engine generates optimal advice based on the prompts and sends it back to the server, which converts the advice into JSON format and sends it to the device as an HTTP response.

[1286] Sentiment Analysis Engine

[1287] The sentiment analysis engine includes an algorithm for analyzing input text data and identifying the emotional state of the user. The algorithm uses natural language processing techniques to identify the emotional state.

[1288] Natural Language Processing Engine

[1289] The natural language processing engine is a software module that generates appropriate advice based on the emotional information obtained from the emotion analysis engine and the user's concerns. Specifically, it uses a generative AI model (e.g., OpenAI's GPT-3).

[1290] Specific examples

[1291] For example, an employee might input into the system a concern such as, "Recently, relationships at work have been strained and I can't concentrate on my work." In this case, the device sends the message to the server, which uses an emotion analysis engine to recognize emotions such as "irritation" or "anxiety." The server then uses a natural language processing engine to generate advice that incorporates the emotional information. The generated advice is sent back to the device via the server and provided to the employee in the form of, "To improve communication with your colleagues, it is important to set up regular opportunities for feedback and strive for open dialogue. Also, pay attention to your own stress management."

[1292] This system allows employees to receive appropriate advice at any time, reducing the amount of time they spend consulting with their superiors and improving their mental health, which is expected to improve workplace health and productivity.

[1293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1294] Step 1:

[1295] The user opens the dedicated application and enters their concerns into a text box. For example, they might enter, "Recently, I've been feeling stressed about interpersonal relationships at work." This input is then passed to the next step.

[1296] Step 2:

[1297] The device receives the text data entered by the user, generates an HTTP POST request, and sends it to the server. This request contains the entered text in JSON format, for example:

[1298] json

[1299] {

[1300] "message": "Recently, I've been feeling stressed about relationships at work."

[1301] }

[1302] This request is passed to the server.

[1303] Step 3:

[1304] The server receives the HTTP POST request sent from the device. It extracts the user's input message from the request body and passes it to the emotion analysis engine. The server then sends the input data to the emotion analysis engine for analysis.

[1305] Step 4:

[1306] The emotion analysis engine analyzes the user's emotional state from the received input message. For example, the emotion analysis engine detects emotions such as "stress" or "anxiety." The analysis result is returned to the server in the following JSON format:

[1307] json

[1308] {

[1309] "emotion": "stress"

[1310] }

[1311] Step 5:

[1312] The server receives the emotion information obtained from the emotion analysis engine and passes it to the natural language processing engine. Specifically, it creates the following prompt to generate a prompt sentence and call the API.

[1313] "The user is concerned about 'I've recently been feeling stressed in my relationships at work,' and the emotion is 'stress.' Please provide appropriate advice."

[1314] This prompt is sent to a natural language processing engine.

[1315] Step 6:

[1316] The natural language processing engine analyzes the prompts and generates optimal advice based on the user's concerns and emotions. For example, it might generate advice such as, "To improve communication with your colleagues, it's important to set up regular opportunities for feedback and maintain open dialogue. Also, pay attention to your own stress management." This advice is then returned to the server.

[1317] Step 7:

[1318] The server receives advice from the natural language processing engine, converts it into JSON format, and sends it to the terminal as an HTTP response. For example, the following data is sent to the terminal:

[1319] json

[1320] {

[1321] "advice": "To improve communication with your colleagues, it's important to foster open dialogue and increase opportunities for feedback. At the same time, be sure to pay attention to your own stress management."

[1322] }

[1323] Step 8:

[1324] The device receives the response from the server and displays the advice within the application. The user can confirm and put into practice this advice, thereby gaining concrete ways to deal with worries and stress in the workplace.

[1325] (Application example 2)

[1326] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1327] In today's workplace, improving employee mental health and motivation is an important issue. However, especially in factories, employees often work 24 hours a day, limiting the time they have to consult with their superiors or colleagues. It is also difficult to grasp the psychological burden of workplace relationships and work-related stress in real time and provide appropriate advice. Therefore, there is a need for a system that can quickly respond to employees' concerns and provide appropriate advice that takes their emotions into consideration.

[1328] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from an employee, means for passing the accepted input content to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice as voice. This makes it possible to grasp the employee's concerns in real time and provide appropriate advice that takes emotions into consideration.

[1329] An "employee" is a worker who works for a company or organization and is employed to carry out duties.

[1330] "Means for accepting input" refers to the interface or system for receiving concerns and questions from employees.

[1331] A "natural language processing engine" is a program that analyzes input text data and understands its meaning and intent.

[1332] "Means for providing answers" refers to the methods and devices used to communicate advice and answers generated by the natural language processing engine to employees.

[1333] "Voice-to-text conversion means" refers to any technology or device used to convert an employee's speech into digital text.

[1334] An "emotion analysis engine" is a program for identifying and analyzing emotions and psychological states from text data.

[1335] "Generative AI model" refers to an artificial intelligence model that generates appropriate advice based on input data.

[1336] "Voice output means" refers to a device or system that converts the generated text advice into voice and transmits it to employees.

[1337] A system for carrying out this invention provides prompt and appropriate advice to employees regarding mental worries and stress. The system includes means for accepting input from employees, means for passing the accepted input to a natural language processing engine, means for providing the employee with a response obtained from the natural language processing engine, means for converting voice input into text, means for extracting emotional information using an emotion analysis engine, means for generating advice based on the emotional information using a generative AI model, and means for outputting the generated advice by voice.

[1338] Server Processing

[1339] The server receives input data sent from the device and passes it to a sentiment analysis engine to extract emotional information. This sentiment analysis engine uses Azure Cognitive Services or similar. The server then queries a natural language processing engine along with the emotional information to generate appropriate advice. This generation uses a generative AI model such as OpenAI's GPT-3.

[1340] For example, if the server receives the input, "Recently, working late-night shifts has been tough and mentally stressful," the emotion analysis engine extracts "stress" as emotional information.The server then sends the following prompt sentence to the generative AI model:

[1341] Example prompt sentence:

[1342] A user is worried about 'lately working late-night shifts has been tough and mentally exhausting' and the emotion they are feeling is 'stress'. Please provide appropriate advice.

[1343] Terminal handling

[1344] The device receives voice input from employees and converts this speech into text using Google's speech recognition API, etc. It also receives the generated advice from the server and provides it to employees in audio format using Google Text-to-Speech, etc.

[1345] For example, if an employee makes a voice input such as "I've been feeling stressed about interpersonal relationships at work recently," the device converts this voice into text and sends it to the server. After receiving the generated advice from the server, the device converts the advice into voice and conveys it to the employee.

[1346] How users use it

[1347] Users talk about their concerns into a microphone built into the robot, and the system converts the speech into text and sends it to the server. The server uses emotion analysis and generative AI models to generate appropriate advice, which the device then relays to the user via voice. This process allows users to receive specific, emotionally appropriate advice in real time.

[1348] In this way, this system can consistently perform everything from voice input to emotion analysis, advice generation, and voice output, making it possible to respond quickly and appropriately to the various workplace worries and stresses that employees face.

[1349] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1350] Step 1:

[1351] The user inputs their concerns by voice. For example, they might say, "Recently, I've been feeling stressed about interpersonal relationships at work." The input is voice data.

[1352] Step 2:

[1353] The device receives voice data and converts it into text using Google's speech recognition API. Specifically, the voice data is sent to the speech recognition engine and text data is obtained. The output is text data.

[1354] Step 3:

[1355] The device sends text data to the server as an HTTP POST request. The request content includes the user's text input. The output is the text data sent to the server.

[1356] Step 4:

[1357] The server passes the received text data to a sentiment analysis engine (e.g., Azure Cognitive Services) to extract emotional information. The sentiment analysis engine identifies emotions (e.g., "stress" or "anxiety") from the text data. The output is emotional information.

[1358] Step 5:

[1359] The server passes the emotion information and text data to a generative AI model (e.g., OpenAI's GPT-3) to generate appropriate advice. The generative AI model creates advice based on the given prompt. The output is the advice text data.

[1360] Step 6:

[1361] The server sends the generated advice to the terminal as an HTTP response. The response content includes the generated advice. The output is the text data of the advice sent to the terminal.

[1362] Step 7:

[1363] The device converts the received text data of advice into speech using the Google Text-to-Speech API. Specifically, the text data is sent to a speech synthesis engine, and speech data is obtained. The output is speech data.

[1364] Step 8:

[1365] The terminal provides the generated voice data to the user through a speaker, and the user receives the advice by voice. The output is the voice advice provided to the user.

[1366] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1367] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1368] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1369] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1370] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1371] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1372] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1373] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1374] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1375] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1376] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1377] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1378] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1379] 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.

[1380] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1381] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1382] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1383] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1384] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1385] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1386] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1387] The following is further disclosed regarding the above embodiment.

[1388] (Claim 1)

[1389] a means for accepting input from employees; and

[1390] A means for passing the received input to a natural language processing engine;

[1391] A way to provide employees with answers derived from the natural language processing engine;

[1392] A system including:

[1393] (Claim 2)

[1394] The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

[1395] (Claim 3)

[1396] 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior.

[1397] "Example 1"

[1398] (Claim 1)

[1399] a means for accepting input from employees; and

[1400] means for transmitting the received input to a server;

[1401] A means for the server to pass the input content to a natural language processing engine and generate a prompt sentence;

[1402] A means for the server to receive advice obtained from the natural language processing engine and provide it to employees;

[1403] A system including:

[1404] (Claim 2)

[1405] The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

[1406] (Claim 3)

[1407] 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior.

[1408] "Application Example 1"

[1409] (Claim 1)

[1410] a means for accepting input from employees; and

[1411] A means for passing the received input to a natural language processing engine;

[1412] A way to provide employees with answers derived from the natural language processing engine;

[1413] A means for using a generative AI model to analyze an input concern;

[1414] A means for creating and sending prompts to the generative AI model;

[1415] A system including:

[1416] (Claim 2)

[1417] The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

[1418] (Claim 3)

[1419] 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior.

[1420] "Example 2: Combining Emotion Engines"

[1421] (Claim 1)

[1422] a means for accepting input from employees; and

[1423] A means for passing the received input to a sentiment analysis engine;

[1424] a means for transferring the emotion information obtained from the emotion analysis engine to a natural language processing engine;

[1425] A way to provide employees with answers derived from the natural language processing engine;

[1426] ...

[1427] A system including:

[1428] (Claim 2)

[1429] The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

[1430] (Claim 3)

[1431] 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior.

[1432] "Application example 2 when combining emotion engines"

[1433] (Claim 1)

[1434] a means for accepting input from employees; and

[1435] A means for passing the received input to a natural language processing engine;

[1436] A way to provide employees with answers derived from the natural language processing engine;

[1437] a means for converting voice input into text;

[1438] means for extracting emotion information using an emotion analysis engine;

[1439] A means for generating advice based on emotion information using a generative AI model;

[1440] means for audibly outputting the generated advice;

[1441] A system including:

[1442] (Claim 2)

[1443] The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

[1444] (Claim 3)

[1445] 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior. [Explanation of symbols]

[1446] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for accepting input from employees; and A means for passing the received input to a natural language processing engine; A way to provide employees with answers derived from the natural language processing engine; A system including:

2. The system according to claim 1, further comprising means for identifying that the input content is a problem consultation.

3. 2. The system according to claim 1, further comprising means for reducing the time spent consulting with a superior.

Images