system

Abstract

We provide the system. [Solution] A means of analyzing user inquiries using a natural language processing model, A means of obtaining relevant data based on analysis results through a database API, A means of formatting acquired data into a user-friendly format and generating responses, A means of sending the generated response to the terminal and displaying it, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is an issue to effectively utilize the information accumulated within a company so that new employees and mid-career employees can efficiently obtain the necessary information. In particular, in conventional sales management and customer relationship management systems, it is difficult for users to quickly access the required information, and insufficient transmission of personal information has been regarded as a problem. This leads to a decrease in business efficiency and the problem that information sharing does not progress.

Means for Solving the Problems

[0005] The system according to the present invention includes means for analyzing user inquiries using a natural language processing model, means for acquiring relevant data based on the analysis results via a database API, means for formatting the acquired data into a user-friendly format to generate an answer, and means for sending and displaying the generated answer on a terminal. This allows users to quickly and accurately obtain the necessary information simply by entering a question through a chat interface. Furthermore, by including means for filtering the acquired relevant data based on specific criteria, it is possible to provide users with more accurate answers. This enables effective utilization of information accumulated within a company, leading to improved information sharing and operational efficiency.

[0006] A "natural language processing model" refers to algorithms and technologies used to analyze text entered by a user and interpret its intent and meaning.

[0007] A "database API" refers to an interface that allows external programs to access a database and retrieve, add, delete, and update data.

[0008] "Related data" refers to data identified based on the user's inquiry and is data related to the information the user is seeking.

[0009] "Formatting" refers to the process of transforming acquired data into a format that is easy for users to understand.

[0010] "Answer" refers to the information generated as a response to a user's inquiry.

[0011] "Device" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0012] A "chat interface" refers to an interactive user interface that allows users to input inquiries in natural language and receive responses from the system.

[0013] "Filtering" refers to the process of selecting only the necessary data from acquired data based on specific criteria.

[0014] "Information accumulated within a company" refers to the collective term for data, knowledge, documents, etc., that a company collects and stores through its business operations.

[0015] "Information sharing" refers to the process of making information held by individuals available to the entire organization. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] This invention relates to a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0038] System Overview

[0039] This system consists of the following main components:

[0040] A terminal equipped with a chat interface for users to enter questions.

[0041] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0042] A database API for retrieving relevant data from a database (e.g., an internal corporate database) based on a question.

[0043] A processing means for organizing acquired data and generating and displaying responses to the user.

[0044] Explanation of the program's processing flow

[0045] 1. The user enters their question through the chat interface.

[0046] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0047] 2. The device sends the question to the natural language processing model.

[0048] The terminal receives the user's question and sends it to the server. The server then passes this question to a natural language processing model, which parses the query.

[0049] 3. The server analyzes the question and retrieves relevant data.

[0050] The server uses a natural language processing model to analyze the intent behind the user's question. This analysis identifies data related to the question (e.g., "top sales," "this month," "sales," etc.). Next, the server uses a database API to retrieve the relevant data from a database such as Salesforce.

[0051] 4. The server organizes the data and generates a response.

[0052] The server organizes the acquired data and formats it into a user-friendly format. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0053] 5. The server sends a response to the terminal.

[0054] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0055] 6. The user confirms the response.

[0056] Users can view the responses displayed in the chat interface through their device.

[0057] Specific example

[0058] When new employee A types "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server uses a natural language processing model to analyze the question and identify keywords such as "top-selling," "this month," and "salesperson." Next, the server uses the Salesforce database API to retrieve the sales data for this month. Based on this data, it generates a response, "The top-selling salesperson this month is B," and sends it to the device. Finally, the device displays this response in the chat interface, allowing new employee A to quickly obtain the necessary information.

[0059] This system allows companies to efficiently utilize internal information and enables new and mid-career employees to quickly access the information they need. Furthermore, it promotes information sharing and contributes to improved operational efficiency.

[0060] The following describes the processing flow.

[0061] Step 1:

[0062] The user enters a question into the chat interface. For example, they might enter the question, "Who is the top-selling salesperson this month?"

[0063] Step 2:

[0064] The terminal receives the user's question. The terminal sends the question data to the server.

[0065] Step 3:

[0066] The server receives the question data. The server inputs that question data into a natural language processing (NLP) model.

[0067] Step 4:

[0068] The server uses an NLP model to analyze the question. As a result of the analysis, it extracts important keywords contained in the question (e.g., "top sales," "this month," "sales").

[0069] Step 5:

[0070] The server generates queries using the database API based on the extracted keywords. For example, it might generate a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0071] Step 6:

[0072] The server generates a query and sends it to the database API. The database API then executes that query against the database (e.g., Salesforce).

[0073] Step 7:

[0074] The database API retrieves relevant data from the database. For example, it retrieves data indicating that the top-selling salesperson is "Mr. B".

[0075] Step 8:

[0076] The server receives the data it has acquired. Based on that data, the server generates a response for the user. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0077] Step 9:

[0078] The server sends the generated response to the terminal.

[0079] Step 10:

[0080] The device displays the response received from the server in the chat interface.

[0081] Step 11:

[0082] The user checks the response displayed through the chat interface on their device. For example, they might read the response, "This month's top salesperson is Mr. / Ms. B."

[0083] (Example 1)

[0084] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Traditional inquiry systems made it difficult for users to quickly access the information they needed, and especially when dealing with large amounts of data within a company, there was a problem of the significant time it took to search for and retrieve information. Furthermore, they lacked the ability to properly interpret natural language inquiries and provide answers in a user-friendly format, resulting in poor user convenience.

[0086] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0087] In this invention, the server includes means for using a natural language processing model to analyze queries, means for using a database interface to acquire data based on the analysis results, and means for formatting the acquired data into a user-friendly format to generate a response. This makes it possible to quickly and accurately analyze the content of queries entered by users in natural language, efficiently acquire related data, and provide responses in an easy-to-understand format.

[0088] A "natural language processing model for analyzing queries" refers to algorithms and technologies that analyze the content of queries entered by users in natural language and understand their intent and meaning.

[0089] A "database interface for retrieving data" is a software component used to retrieve necessary information from a database, and it has the functionality to communicate with the database through APIs and queries.

[0090] "Means of formatting data into a user-friendly format and generating responses" refers to the processing and technologies used to organize acquired data in a way that is easily understandable to users and to display it in an appropriate manner.

[0091] A "user terminal" is a device used by a user to access the system and input / confirm their inquiry details, and includes personal computers, smartphones, tablets, and other similar devices.

[0092] This invention relates to a system that allows users to quickly access information within a company. This system consists of user terminals, servers, and database APIs as its main components.

[0093] System Configuration

[0094] This system consists of the following main components:

[0095] 1. User Terminal: Equipped with a chat interface for users to input their inquiries. User terminals can be a wide variety of devices, including personal computers, smartphones, and tablets.

[0096] 2. Server: Receives user queries and performs analysis using a natural language processing model. The server understands the intent of the query and retrieves the necessary data via a database API based on that understanding.

[0097] 3. Database API: A software component for accessing an internal enterprise database and retrieving data based on a specified query.

[0098] Program operation

[0099] 1. The user enters a question into the chat interface.

[0100] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0101] 2. The device sends the question to the natural language processing model.

[0102] The terminal sends the received question to the server. After receiving the question, the server passes it to a natural language processing model for analysis.

[0103] 3. The server analyzes the question and retrieves relevant data.

[0104] The server analyzes the question using a natural language processing model (e.g., GPT-3®). This analysis identifies keywords such as "top sales," "this month," and "sales." Based on these keywords, the server retrieves relevant data from the company's internal database using a database API.

[0105] 4. The server organizes the data and generates a response.

[0106] The server organizes the acquired data and formats it into a user-friendly format. For example, it generates specific answers such as, "This month's top salesperson is Mr. / Ms. B."

[0107] 5. The server sends a response to the terminal.

[0108] The server sends the generated response to the terminal. The terminal displays the response in the chat interface.

[0109] 6. The user confirms the response.

[0110] The user checks the response displayed in the chat interface through their device.

[0111] Specific examples of hardware and software to be used

[0112] Hardware: User devices such as personal computers, smartphones, and tablets.

[0113] Software: Natural language processing models (e.g., GPT-3), database APIs (e.g., Salesforce API), chat interfaces, etc.

[0114] Specific example

[0115] If new employee A enters "Who is the top-selling salesperson this month?", the following steps will be executed.

[0116] 1. The user terminal sends the question to the server.

[0117] 2. The server uses a natural language processing model to analyze the question and identify keywords such as "top sales," "this month," and "sales."

[0118] 3. The server uses the database API to retrieve this month's sales data.

[0119] 4. The server organizes the acquired data and generates a response stating, "This month's top-selling salesperson is Mr. / Ms. B."

[0120] 5. The device receives a response from the server and displays it in the chat interface.

[0121] 6. The user confirms the response.

[0122] Example of a prompt

[0123] "Who is the top-selling salesperson this month?"

[0124] This system enables quick and efficient searching and retrieval of necessary information within a company, improving convenience for users.

[0125] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0126] Specific processing steps of the program for this system

[0127] Step 1:

[0128] The user enters a question into the chat interface.

[0129] Input: Users enter their questions in natural language into the chat interface. Example: "Who is the top-selling salesperson this month?"

[0130] Operation: The terminal receives the text entered by the user and temporarily stores it in an internal buffer.

[0131] Output: Text data of the saved questions.

[0132] Step 2:

[0133] The device sends the question to the natural language processing model.

[0134] Input: Text data of the saved question.

[0135] Operation: The terminal uses an HTTP POST request to send the question text to the server.

[0136] Output: Request data of the question text sent to the server.

[0137] Step 3:

[0138] The server analyzes the question and extracts relevant keywords.

[0139] Input: Request data of the question text received from the terminal.

[0140] Operation: The server uses a natural language processing model (e.g., GPT-3) to analyze the question text. Through this analysis, keywords such as "top sales," "this month," and "sales" are extracted.

[0141] Output: Extracted keyword data.

[0142] Step 4:

[0143] The server retrieves relevant data from the database.

[0144] Input: Extracted keyword data.

[0145] Operation: The server uses a database API (e.g., an enterprise database API) to generate keyword-based queries and retrieve relevant data from a database such as Salesforce.

[0146] Output: The retrieved related data.

[0147] Step 5:

[0148] The server organizes the data and generates a response.

[0149] Input: The retrieved related data.

[0150] Operation: The server analyzes and organizes the acquired data and generates a response in a format that is easy for the user to understand. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0151] Output: Organized response data.

[0152] Step 6:

[0153] The server sends a response to the terminal.

[0154] Input: Organized response data.

[0155] Operation: The server encodes the response data in JSON format and sends it to the terminal as an HTTP response.

[0156] Output: Response data sent to the terminal.

[0157] Step 7:

[0158] The device displays the reply in the chat interface.

[0159] Input: Response data sent to the terminal.

[0160] Operation: The device analyzes the received response data and displays it in the chat interface.

[0161] Output: The response displayed in the chat interface.

[0162] Step 8:

[0163] The user confirms the response.

[0164] Input: The response displayed in the chat interface.

[0165] Operation: The user checks the response displayed in the device's chat interface.

[0166] Output: The response confirmed by the user.

[0167] Through these steps, the system can analyze user inquiries in natural language, quickly and efficiently retrieve the necessary data, and provide clear and understandable answers.

[0168] (Application Example 1)

[0169] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0170] In logistics centers, there is a problem where staff have difficulty quickly obtaining necessary information, leading to decreased operational efficiency. Furthermore, the lack of real-time information access makes it difficult to respond quickly on-site.

[0171] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0172] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for acquiring relevant data based on the analysis results via a database API, means for formatting the acquired data into a user-friendly format and generating a response, means for sending and displaying the generated response on a terminal, and means for enabling users to check logistics-related information in real time via an interface. This allows staff to easily acquire necessary information, improve operational efficiency, and enable rapid, real-time responses.

[0173] A "natural language processing model" is a machine learning algorithm used to understand and analyze natural language.

[0174] "User inquiries" refer to questions and requests that users enter into the system.

[0175] A "database API" is an interface that allows different software systems to exchange data with each other.

[0176] "Related data" refers to information that the server needs to identify and retrieve in response to a user's inquiry.

[0177] A "response" is the result of providing information generated in response to a user's inquiry.

[0178] A "device" refers to a device used by a user, such as a smartphone, smart glasses, or computer.

[0179] "Logistics-related information" refers to data related to logistics center operations, such as inventory status, shipping status, receiving status, and delivery status.

[0180] "Real-time" refers to processing and data updates that occur almost simultaneously.

[0181] An "interface" is a means or method for exchanging information between a user and a system.

[0182] This invention is a system for improving information acquisition and operational efficiency in logistics centers. This system is implemented by integrating a natural language processing model, a database API, and a chat interface.

[0183] Hardware and software to be used

[0184] Hardware: Smartphones, smart glasses, servers

[0185] Software: Chat interface, natural language processing models (e.g., GPT-4®), database APIs (e.g., SQL-based inventory management systems)

[0186] System Configuration

[0187] 1. User inquiry input

[0188] Users (for example, staff at a logistics center) enter work-related questions using a chat interface on their smartphone or smart glasses. For example, they might ask questions like the following:

[0189] "What is the shipping status for today?"

[0190] "Please tell me the current stock level."

[0191] 2. Natural Language Processing and Data Acquisition

[0192] The terminal sends the user's question to the server. The server uses a natural language processing model (e.g., GPT-4) to analyze the user's inquiry. This analysis identifies relevant keywords (e.g., "shipping status," "inventory level"). Next, the server uses a database API to retrieve the necessary information from a database related to the logistics center (e.g., a SQL-based inventory management system).

[0193] 3. Answer generation and display

[0194] The server organizes the retrieved data and formats it into a user-friendly format. For example, if information about shipping status is retrieved, it might be formatted as "Today's shipping status is as follows." The generated response is then sent back to the terminal and displayed in the user's chat interface.

[0195] Specific example

[0196] For example, if a staff member at a logistics center wants to check the inventory count using smart glasses, they would input a prompt message like the following into the AI ​​model that generates the inventory:

[0197] Example of a prompt

[0198] User question: "What is the current stock level?"

[0199] Answer: "We currently have 120 units left in stock."

[0200] Please identify the relevant data.

[0201] By using this prompt, the natural language processing model identifies the "inventory quantity," generates an appropriate database query to retrieve the inventory quantity, and then generates and displays the final response. This allows for more efficient operations at the logistics center and enables real-time information access.

[0202] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0203] Step 1:

[0204] The user enters their inquiry into the chat interface using a device (smartphone or smart glasses). For example, they might enter the question, "What is the current stock quantity?" This input is stored on the device in text format.

[0205] Step 2:

[0206] The terminal sends the entered query content to the server. Metadata such as the user ID and timestamp are also sent along with it. This input data is received by the server and passed on to the next processing step.

[0207] Step 3:

[0208] The server passes the received query content to a natural language processing model (e.g., GPT-4) for analysis. Specifically, it extracts relevant keywords (e.g., "inventory quantity") from the query content and understands the intent. This process identifies the type of data that should be retrieved. The output consists of the identified keywords and intent.

[0209] Step 4:

[0210] The server calls a database API based on identified keywords and intents to retrieve relevant data. For example, to retrieve data about "inventory levels," it sends a query to a SQL-based inventory management system. The input is the identified keywords, and the output is inventory level data as the query result.

[0211] Step 5:

[0212] The server formats the retrieved data into a format that is easy for the user to understand. Specifically, it converts the retrieved inventory data into a format such as "Current inventory: 120 units remaining." At this stage, the input is the raw query result data, and the output is formatted text data.

[0213] Step 6:

[0214] The server sends the generated response to the terminal. The terminal displays the received response in the chat interface. This allows the user to quickly obtain the necessary information. In this final step, the input is the formatted response text, and the output is the information displayed on the user's terminal.

[0215] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0216] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0217] System Overview

[0218] This system consists of the following main components:

[0219] A terminal equipped with a chat interface for users to enter questions.

[0220] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0221] Database API for retrieving related data from a database

[0222] A processing means for organizing acquired data and generating and displaying responses to the user.

[0223] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0224] Explanation of the program's processing flow

[0225] 1. The user enters their question through the chat interface.

[0226] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0227] 2. The device sends the question to the natural language processing model and sentiment engine.

[0228] The terminal receives the user's question and sends it to the server. The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the inquiry and the user's sentiment.

[0229] 3. The server analyzes the question and retrieves relevant data.

[0230] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0231] 4. The server analyzes the user's emotions using an emotion engine.

[0232] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0233] 5. The server organizes the data and generates a response that takes emotions into account.

[0234] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0235] 6. The server sends a response to the terminal.

[0236] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0237] 7. The user confirms the response.

[0238] The user checks the response displayed in the chat interface through their device. For example, they might see a response like, "Don't worry, B is the top-selling salesperson this month."

[0239] Specific example

[0240] When new employee A enters the question "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server analyzes the question using an NLP model and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Meanwhile, an emotion engine analyzes new employee A's emotions (e.g., nervousness or reassurance). Based on the retrieved data and the emotion analysis results, the server generates a response such as "The top-selling salesperson this month is B." Furthermore, based on the analysis results from the emotion engine, it can create an emotion-sensitive response such as "Don't worry, B is the top-selling salesperson this month." Finally, the device displays this response in the chat interface, allowing new employee A to quickly and appropriately obtain the necessary information.

[0241] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The user enters a question into the chat interface. For example, they might type, "Who is the top-selling salesperson this month?"

[0245] Step 2:

[0246] The terminal receives the user's question. It sends the received question to the server.

[0247] Step 3:

[0248] The server receives the question data. The server simultaneously sends this data to the natural language processing (NLP) model and the emotion engine.

[0249] Step 4:

[0250] The server uses an NLP model to analyze the question. For example, it extracts important keywords such as "top sales," "this month," and "sales."

[0251] Step 5:

[0252] The server generates queries using the database API based on the extracted keywords. For example, it generates a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0253] Step 6:

[0254] The server sends the generated query to the database API. The database API executes the query and retrieves the relevant data.

[0255] Step 7:

[0256] The database API retrieves data from the database, for example, "Person B is the top-selling salesperson this month." The server receives this data.

[0257] Step 8:

[0258] The server analyzes the user's emotions using an emotion engine. The emotion engine identifies the user's emotions (e.g., relief, tension, anxiety, etc.) from the text.

[0259] Step 9:

[0260] Based on the data acquired by the server and the sentiment analysis results, it generates a response for the user. For example, if it detects that the user is feeling anxious, it will generate a response in the format of, "Don't worry, salesperson B is the top seller this month."

[0261] Step 10:

[0262] The server sends the generated response to the terminal. The terminal receives this response.

[0263] Step 11:

[0264] The terminal displays the response received from the server in the chat interface. The user then reviews this response.

[0265] Step 12:

[0266] Users read the responses displayed in the chat interface through their device. For example, by confirming a response such as, "Don't worry, B is the top-selling salesperson this month," they can quickly and appropriately obtain information.

[0267] (Example 2)

[0268] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0269] Conventional information retrieval systems have struggled to properly analyze user inquiries and efficiently retrieve relevant data. Furthermore, they have been unable to generate responses that take user emotions into account, resulting in a failure to provide users with appropriate and effective information. Especially when inquiries are complex or influenced by user emotions, more advanced analysis and responses are required.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0271] In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for obtaining relevant data based on the analysis results via a database API, means for formatting the obtained data into a user-friendly format and generating an answer, means for sending and displaying the generated answer on a terminal, and an emotion engine that recognizes the user's emotions and reflects them in the analysis results. This makes it possible to provide appropriate information that takes into account not only the user's inquiry but also their emotions.

[0272] A "natural language processing model" is an algorithm that analyzes user inquiries and extracts important keywords and meanings.

[0273] A "database API" is an interface for accessing a database and retrieving necessary data.

[0274] An "emotion engine" is a system that recognizes emotions from the content of a user's inquiry and reflects them in the analysis results.

[0275] The "chat interface" refers to an interactive input means through which a user can input inquiry content in natural language.

[0276] The "analysis result" refers to the meaning and sentiment of the user's inquiry content analyzed by a natural language processing model or a sentiment engine.

[0277] The "related data" refers to information related to the user's inquiry content obtained through a database API.

[0278] The "answer generation means" refers to a method for generating content to be returned to the user based on the analysis result.

[0279] The "display means" refers to a method or system for visually providing the generated answer to the user.

[0280] The present invention combines a sentiment engine with a system that enables a user to quickly access information within an enterprise. Hereinafter, specific embodiments of this system will be described in detail.

[0281] Overview of the System

[0282] This system is composed of the following main components.

[0283] A terminal equipped with a chat interface for a user to input questions

[0284] A server equipped with a natural language processing model for analyzing a user's question and identifying appropriate data

[0285] A database API for obtaining related data from a database

[0286] Processing means for sorting the obtained data and generating and displaying a response to the user

[0287] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0288] Program processing flow

[0289] The user uses their device to enter a question into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?" The device receives this question and sends it to the server.

[0290] The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the query content and the user's sentiment. OpenAI®'s GPT-3 and BERT can be used as natural language processing models for analysis. IBM Watson® and Azure® Cognitive Services are available as sentiment engines.

[0291] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0292] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0293] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0294] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface. The user checks the response displayed in the chat interface through their terminal.

[0295] Specific example

[0296] A new employee enters the question, "Who is the top-selling salesperson this month?" into the chat interface. The terminal sends this question to the server. The server analyzes the question using an NLP model (e.g., GPT-3) and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Simultaneously, it analyzes the new employee's emotions using an emotion engine (e.g., IBM Watson) and detects anxiety. Based on the retrieved data and the emotion analysis results, the server generates a basic response, "The top-selling salesperson this month is Mr. / Ms. B," and adds supplementary explanations such as "Don't worry." Finally, it sends the response to the terminal, and the new employee can check the response through the chat interface.

[0297] Examples of prompt statements include the following:

[0298] "Who is the top-selling salesperson this month?"

[0299] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0300] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0301] Step 1:

[0302] The user enters a question into the terminal's chat interface. For example, the user might type, "Who is the top-selling salesperson this month?" The input data is the user's inquiry.

[0303] Step 2:

[0304] The terminal receives the user's question and sends it to the server. Specifically, the terminal uses an HTTP request to send the user's question data to the server. The input is the question entered by the user, and the output is the question data sent to the server.

[0305] Step 3:

[0306] The server receives the question data, passes it to the natural language processing model for analysis. The server uses an NLP model (e.g., GPT-3) to analyze the intent of the question and extract important keywords (e.g., "sales top", "this month", "sales"). The input is the user's question data, and the output is the list of analyzed keywords.

[0307] Step 4:

[0308] Based on the keywords extracted by the server, the server uses the database API to obtain relevant data. Specifically, the server queries data related to "this month's sales top sales" through the Salesforce API. The input is the keyword list, and the output is the relevant data obtained from the database.

[0309] Step 5:

[0310] The server passes the content of the question to the sentiment engine to analyze the user's sentiment. Using a sentiment engine (e.g., IBM Watson), it recognizes whether the user has emotions such as anxiety, joy, or doubt. The input is the user's question data, and the output is the analyzed sentiment data.

[0311] Step 6:

[0312] The server generates a response based on the relevant data and the sentiment analysis result. The server uses an NLG engine to generate an appropriate response based on the obtained data and the sentiment analysis result. For example, it creates a response such as "Please rest assured, the top salesperson this month is Mr. B". The input is the relevant data and the sentiment data, and the output is the generated response.

[0313] Step 7:

[0314] The server sends the generated response to the terminal. The server sends the response to the terminal as an HTTP response, which the terminal receives and displays to the user. The input is the generated response data, and the output is the response sent to the terminal.

[0315] Step 8:

[0316] The user confirms the response through the chat interface on their device. For example, the user might confirm a response such as, "Don't worry, B is the top salesperson this month." The input is the response data sent from the server, and the output is the response that the user confirms.

[0317] (Application Example 2)

[0318] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0319] Current information management systems in factories often make it difficult for workers to quickly and accurately access the information they need. Furthermore, they fail to consider the emotional state of workers, leading to unclear responses or inappropriate actions. This can reduce work efficiency and increase the likelihood of errors. This invention aims to solve these problems and achieve efficient and appropriate information management.

[0320] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for acquiring relevant data based on the analysis results through a database API, means for formatting the acquired data into a format easily understood by the user and generating an answer, means including an emotion engine that analyzes the user's emotional state and adjusts the answer based on the analysis results, and means for transmitting and displaying the generated answer on a terminal. This makes it possible for workers to quickly and accurately access the information they need and obtain appropriate answers according to their emotional state.

[0321] A "natural language processing model" is an algorithm or machine learning model used to analyze user inquiries.

[0322] A "database API" is an application programming interface that enables access to databases and retrieval of data.

[0323] "Related data" refers to necessary information retrieved from the database based on the user's inquiry.

[0324] "Answer" refers to information provided to the user using the relevant data that has been acquired.

[0325] "Emotional state" refers to the emotional state analyzed from the user's input.

[0326] An "emotion engine" is an engine that analyzes the user's emotional state and adjusts its responses based on the analysis results.

[0327] A "chat interface" is an interface used by users to input their inquiries.

[0328] "Terminal" refers to electronic devices such as computers and mobile devices used by users.

[0329] "Analysis results" refer to the data and information obtained using natural language processing models and database APIs.

[0330] "Formatting" is the process of converting acquired data and information into a format that is easy for users to understand.

[0331] "Means" refers to methods or devices used to achieve a specific function or purpose.

[0332] This invention is a system that streamlines information management within a factory and provides appropriate responses based on the emotional state of workers. Specific embodiments are described below.

[0333] System Overview

[0334] This system consists of the following main components:

[0335] A terminal equipped with a chat interface for users to enter questions.

[0336] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0337] Database API for retrieving related data from a database

[0338] A processing means for organizing acquired data and generating and displaying responses to the user.

[0339] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0340] Hardware and software to use

[0341] Device: A computer or mobile device operated by a user.

[0342] Server: A computer server equipped with high-performance computing resources.

[0343] Natural language processing models: For example, machine learning models such as the BERT model.

[0344] Database: Data management system within a factory (e.g., production planning database)

[0345] Emotion engine: A dedicated library or API for analyzing a user's emotional state (e.g., Sentiment Analysis API).

[0346] Program processing

[0347] The server receives the inquiry entered by the user through the terminal and analyzes the question using a natural language processing model. It extracts important keywords from the analyzed content and retrieves relevant data using a database API. Simultaneously, the emotion engine analyzes the user's emotional state, and based on that information, an optimal response is generated. This ensures that responses are tailored to the user's emotional state.

[0348] Specific examples of the system

[0349] For example, if a new worker asks, "Could you tell me this week's production plan?", the statement is transcribed into text using speech recognition. The server analyzes it using a natural language processing model and an emotion engine, and retrieves relevant production plan data from the database. The final result is displayed as, "Don't worry, this week's production plan is on track," providing the worker with appropriate information.

[0350] Example of a prompt

[0351] The prompt statement is the text input to the generative AI model, and is written as follows:

[0352] "Analyze the following text to identify key keywords (production plan, this week) and the user's sentiment: 'Please tell me this week's production plan.'"

[0353] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0354] Step 1:

[0355] The user enters a question through the chat interface. The input can be in text or voice format. In the case of voice input, speech recognition software converts the speech to text. The entered question (e.g., "Please tell me this week's production plan") is sent from the terminal to the server.

[0356] Step 2:

[0357] The server passes the received question to a natural language processing (NLP) model. The NLP model analyzes the question and extracts key keywords (e.g., "this week," "production plan"). This analysis uses machine learning algorithms to understand the context of the text and grasp the user's intent. The analysis results in the extracted keywords.

[0358] Step 3:

[0359] The server calls a database API based on the analysis results to retrieve relevant data. The server generates a query containing keywords and sends it to the database. The database searches based on the query and returns the corresponding production plan data. The retrieved data (e.g., details of this week's production plan) is returned to the server.

[0360] Step 4:

[0361] The server uses an emotion engine to analyze the user's emotional state. The input question text is passed to the emotion engine, which identifies the corresponding emotion (e.g., reassurance, anxiety, excitement) from the text. The emotion engine then uses an emotion analysis algorithm to evaluate the user's emotional state. The analysis results in the user's emotional information.

[0362] Step 5:

[0363] The server integrates acquired data with sentiment analysis results to generate appropriate responses for the user. A data formatting algorithm is used to transform production plan data into a user-friendly format. The response is adjusted according to the user's emotional state to create an emotionally sensitive message (e.g., "Don't worry, this week's production plan is on track"). The generated response is stored on the server.

[0364] Step 6:

[0365] The server sends the generated response to the device. The device then displays the response again in the chat interface. This allows the user to quickly and appropriately obtain the necessary information. After the response is displayed, the user can take the next action based on the information.

[0366] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0367] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0368] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0369] [Second Embodiment]

[0370] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0371] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0372] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0373] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0374] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0375] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0376] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0377] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0378] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0379] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0380] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0381] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0382] This invention relates to a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0383] System Overview

[0384] This system consists of the following main components:

[0385] A terminal equipped with a chat interface for users to enter questions.

[0386] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0387] A database API for retrieving relevant data from a database (e.g., an internal corporate database) based on a question.

[0388] A processing means for organizing acquired data and generating and displaying responses to the user.

[0389] Explanation of the program's processing flow

[0390] 1. The user enters their question through the chat interface.

[0391] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0392] 2. The device sends the question to the natural language processing model.

[0393] The terminal receives the user's question and sends it to the server. The server then passes this question to a natural language processing model, which parses the query.

[0394] 3. The server analyzes the question and retrieves relevant data.

[0395] The server uses a natural language processing model to analyze the intent behind the user's question. This analysis identifies data related to the question (e.g., "top sales," "this month," "sales," etc.). Next, the server uses a database API to retrieve the relevant data from a database such as Salesforce.

[0396] 4. The server organizes the data and generates a response.

[0397] The server organizes the acquired data and formats it into a user-friendly format. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0398] 5. The server sends a response to the terminal.

[0399] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0400] 6. The user confirms the response.

[0401] Users can view the responses displayed in the chat interface through their device.

[0402] Specific example

[0403] When new employee A types "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server uses a natural language processing model to analyze the question and identify keywords such as "top-selling," "this month," and "salesperson." Next, the server uses the Salesforce database API to retrieve the sales data for this month. Based on this data, it generates a response, "The top-selling salesperson this month is B," and sends it to the device. Finally, the device displays this response in the chat interface, allowing new employee A to quickly obtain the necessary information.

[0404] This system allows companies to efficiently utilize internal information and enables new and mid-career employees to quickly access the information they need. Furthermore, it promotes information sharing and contributes to improved operational efficiency.

[0405] The following describes the processing flow.

[0406] Step 1:

[0407] The user enters a question into the chat interface. For example, they might enter the question, "Who is the top-selling salesperson this month?"

[0408] Step 2:

[0409] The terminal receives the user's question. The terminal sends the question data to the server.

[0410] Step 3:

[0411] The server receives the question data. The server inputs that question data into a natural language processing (NLP) model.

[0412] Step 4:

[0413] The server uses an NLP model to analyze the question. As a result of the analysis, it extracts important keywords contained in the question (e.g., "top sales," "this month," "sales").

[0414] Step 5:

[0415] The server generates queries using the database API based on the extracted keywords. For example, it might generate a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0416] Step 6:

[0417] The server generates a query and sends it to the database API. The database API then executes that query against the database (e.g., Salesforce).

[0418] Step 7:

[0419] The database API retrieves relevant data from the database. For example, it retrieves data indicating that the top-selling salesperson is "Mr. B".

[0420] Step 8:

[0421] The server receives the data it has acquired. Based on that data, the server generates a response for the user. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0422] Step 9:

[0423] The server sends the generated response to the terminal.

[0424] Step 10:

[0425] The device displays the response received from the server in the chat interface.

[0426] Step 11:

[0427] The user checks the response displayed through the chat interface on their device. For example, they might read the response, "This month's top salesperson is Mr. / Ms. B."

[0428] (Example 1)

[0429] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0430] Traditional inquiry systems made it difficult for users to quickly access the information they needed, and especially when dealing with large amounts of data within a company, there was a problem of the significant time it took to search for and retrieve information. Furthermore, they lacked the ability to properly interpret natural language inquiries and provide answers in a user-friendly format, resulting in poor user convenience.

[0431] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0432] In this invention, the server includes means for using a natural language processing model to analyze queries, means for using a database interface to acquire data based on the analysis results, and means for formatting the acquired data into a user-friendly format to generate a response. This makes it possible to quickly and accurately analyze the content of queries entered by users in natural language, efficiently acquire related data, and provide responses in an easy-to-understand format.

[0433] A "natural language processing model for analyzing queries" refers to algorithms and technologies that analyze the content of queries entered by users in natural language and understand their intent and meaning.

[0434] A "database interface for retrieving data" is a software component used to retrieve necessary information from a database, and it has the functionality to communicate with the database through APIs and queries.

[0435] "Means of formatting data into a user-friendly format and generating responses" refers to the processing and technologies used to organize acquired data in a way that is easily understandable to users and to display it in an appropriate manner.

[0436] A "user terminal" is a device used by a user to access the system and input / confirm their inquiry details, and includes personal computers, smartphones, tablets, and other similar devices.

[0437] This invention relates to a system that allows users to quickly access information within a company. This system consists of user terminals, servers, and database APIs as its main components.

[0438] System Configuration

[0439] This system consists of the following main components:

[0440] 1. User Terminal: Equipped with a chat interface for users to input their inquiries. User terminals can be a wide variety of devices, including personal computers, smartphones, and tablets.

[0441] 2. Server: Receives user queries and performs analysis using a natural language processing model. The server understands the intent of the query and retrieves the necessary data via a database API based on that understanding.

[0442] 3. Database API: A software component for accessing an internal enterprise database and retrieving data based on a specified query.

[0443] Program operation

[0444] 1. The user enters a question into the chat interface.

[0445] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0446] 2. The device sends the question to the natural language processing model.

[0447] The terminal sends the received question to the server. After receiving the question, the server passes it to a natural language processing model for analysis.

[0448] 3. The server analyzes the question and retrieves relevant data.

[0449] The server analyzes the question using a natural language processing model (e.g., GPT-3). This analysis identifies keywords such as "top sales," "this month," and "sales." Based on these keywords, the server uses a database API to retrieve relevant data from the company's internal database.

[0450] 4. The server organizes the data and generates a response.

[0451] The server organizes the acquired data and formats it into a user-friendly format. For example, it generates specific answers such as, "This month's top salesperson is Mr. / Ms. B."

[0452] 5. The server sends a response to the terminal.

[0453] The server sends the generated response to the terminal. The terminal displays the response in the chat interface.

[0454] 6. The user confirms the response.

[0455] The user checks the response displayed in the chat interface through their device.

[0456] Specific examples of hardware and software to be used

[0457] Hardware: User devices such as personal computers, smartphones, and tablets.

[0458] Software: Natural language processing models (e.g., GPT-3), database APIs (e.g., Salesforce API), chat interfaces, etc.

[0459] Specific example

[0460] If new employee A enters "Who is the top-selling salesperson this month?", the following steps will be executed.

[0461] 1. The user terminal sends the question to the server.

[0462] 2. The server uses a natural language processing model to analyze the question and identify keywords such as "top sales," "this month," and "sales."

[0463] 3. The server uses the database API to retrieve this month's sales data.

[0464] 4. The server organizes the acquired data and generates a response stating, "This month's top-selling salesperson is Mr. / Ms. B."

[0465] 5. The device receives a response from the server and displays it in the chat interface.

[0466] 6. The user confirms the response.

[0467] Example of a prompt

[0468] "Who is the top-selling salesperson this month?"

[0469] This system enables quick and efficient searching and retrieval of necessary information within a company, improving convenience for users.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Specific processing steps of the program for this system

[0472] Step 1:

[0473] The user enters a question into the chat interface.

[0474] Input: Users enter their questions in natural language into the chat interface. Example: "Who is the top-selling salesperson this month?"

[0475] Operation: The terminal receives the text entered by the user and temporarily stores it in an internal buffer.

[0476] Output: Text data of the saved questions.

[0477] Step 2:

[0478] The device sends the question to the natural language processing model.

[0479] Input: Text data of the saved question.

[0480] Operation: The terminal uses an HTTP POST request to send the question text to the server.

[0481] Output: Request data of the question text sent to the server.

[0482] Step 3:

[0483] The server analyzes the question and extracts relevant keywords.

[0484] Input: Request data of the question text received from the terminal.

[0485] Operation: The server uses a natural language processing model (e.g., GPT-3) to analyze the question text. Through this analysis, keywords such as "top sales," "this month," and "sales" are extracted.

[0486] Output: Extracted keyword data.

[0487] Step 4:

[0488] The server retrieves relevant data from the database.

[0489] Input: Extracted keyword data.

[0490] Operation: The server uses a database API (e.g., an enterprise database API) to generate keyword-based queries and retrieve relevant data from a database such as Salesforce.

[0491] Output: The retrieved related data.

[0492] Step 5:

[0493] The server organizes the data and generates a response.

[0494] Input: The retrieved related data.

[0495] Operation: The server analyzes and organizes the acquired data and generates a response in a format that is easy for the user to understand. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0496] Output: Organized response data.

[0497] Step 6:

[0498] The server sends a response to the terminal.

[0499] Input: Organized response data.

[0500] Operation: The server encodes the response data in JSON format and sends it to the terminal as an HTTP response.

[0501] Output: Response data sent to the terminal.

[0502] Step 7:

[0503] The device displays the reply in the chat interface.

[0504] Input: Response data sent to the terminal.

[0505] Operation: The device analyzes the received response data and displays it in the chat interface.

[0506] Output: The response displayed in the chat interface.

[0507] Step 8:

[0508] The user confirms the response.

[0509] Input: The response displayed in the chat interface.

[0510] Operation: The user checks the response displayed in the device's chat interface.

[0511] Output: The response confirmed by the user.

[0512] Through these steps, the system can analyze user inquiries in natural language, quickly and efficiently retrieve the necessary data, and provide clear and understandable answers.

[0513] (Application Example 1)

[0514] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0515] In logistics centers, there is a problem where staff have difficulty quickly obtaining necessary information, leading to decreased operational efficiency. Furthermore, the lack of real-time information access makes it difficult to respond quickly on-site.

[0516] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0517] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for acquiring relevant data based on the analysis results via a database API, means for formatting the acquired data into a user-friendly format and generating a response, means for sending and displaying the generated response on a terminal, and means for enabling users to check logistics-related information in real time via an interface. This allows staff to easily acquire necessary information, improve operational efficiency, and enable rapid, real-time responses.

[0518] A "natural language processing model" is a machine learning algorithm used to understand and analyze natural language.

[0519] "User inquiries" refer to questions and requests that users enter into the system.

[0520] A "database API" is an interface that allows different software systems to exchange data with each other.

[0521] "Related data" refers to information that the server needs to identify and retrieve in response to a user's inquiry.

[0522] A "response" is the result of providing information generated in response to a user's inquiry.

[0523] A "device" refers to a device used by a user, such as a smartphone, smart glasses, or computer.

[0524] "Logistics-related information" refers to data related to logistics center operations, such as inventory status, shipping status, receiving status, and delivery status.

[0525] "Real-time" refers to processing and data updates that occur almost simultaneously.

[0526] An "interface" is a means or method for exchanging information between a user and a system.

[0527] This invention is a system for improving information acquisition and operational efficiency in logistics centers. This system is implemented by integrating a natural language processing model, a database API, and a chat interface.

[0528] Hardware and software to be used

[0529] Hardware: Smartphones, smart glasses, servers

[0530] Software: Chat interface, natural language processing models (e.g., GPT-4), database APIs (e.g., SQL-based inventory management systems)

[0531] System Configuration

[0532] 1. User inquiry input

[0533] Users (for example, staff at a logistics center) enter work-related questions using a chat interface on their smartphone or smart glasses. For example, they might ask questions like the following:

[0534] "What is the shipping status for today?"

[0535] "Please tell me the current stock level."

[0536] 2. Natural Language Processing and Data Acquisition

[0537] The terminal sends the user's question to the server. The server uses a natural language processing model (e.g., GPT-4) to analyze the user's inquiry. This analysis identifies relevant keywords (e.g., "shipping status," "inventory level"). Next, the server uses a database API to retrieve the necessary information from a database related to the logistics center (e.g., a SQL-based inventory management system).

[0538] 3. Answer generation and display

[0539] The server organizes the retrieved data and formats it into a user-friendly format. For example, if information about shipping status is retrieved, it might be formatted as "Today's shipping status is as follows." The generated response is then sent back to the terminal and displayed in the user's chat interface.

[0540] Specific example

[0541] For example, if a staff member at a logistics center wants to check the inventory count using smart glasses, they would input a prompt message like the following into the AI ​​model that generates the inventory:

[0542] Example of a prompt

[0543] User question: "What is the current stock level?"

[0544] Answer: "We currently have 120 units left in stock."

[0545] Please identify the relevant data.

[0546] By using this prompt, the natural language processing model identifies the "inventory quantity," generates an appropriate database query to retrieve the inventory quantity, and then generates and displays the final response. This allows for more efficient operations at the logistics center and enables real-time information access.

[0547] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0548] Step 1:

[0549] The user enters their inquiry into the chat interface using a device (smartphone or smart glasses). For example, they might enter the question, "What is the current stock quantity?" This input is stored on the device in text format.

[0550] Step 2:

[0551] The terminal sends the entered query content to the server. Metadata such as the user ID and timestamp are also sent along with it. This input data is received by the server and passed on to the next processing step.

[0552] Step 3:

[0553] The server passes the received query content to a natural language processing model (e.g., GPT-4) for analysis. Specifically, it extracts relevant keywords (e.g., "inventory quantity") from the query content and understands the intent. This process identifies the type of data that should be retrieved. The output consists of the identified keywords and intent.

[0554] Step 4:

[0555] The server calls a database API based on identified keywords and intents to retrieve relevant data. For example, to retrieve data about "inventory levels," it sends a query to a SQL-based inventory management system. The input is the identified keywords, and the output is inventory level data as the query result.

[0556] Step 5:

[0557] The server formats the retrieved data into a format that is easy for the user to understand. Specifically, it converts the retrieved inventory data into a format such as "Current inventory: 120 units remaining." At this stage, the input is the raw query result data, and the output is formatted text data.

[0558] Step 6:

[0559] The server sends the generated response to the terminal. The terminal displays the received response in the chat interface. This allows the user to quickly obtain the necessary information. In this final step, the input is the formatted response text, and the output is the information displayed on the user's terminal.

[0560] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0561] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0562] System Overview

[0563] This system consists of the following main components:

[0564] A terminal equipped with a chat interface for users to enter questions.

[0565] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0566] Database API for retrieving related data from a database

[0567] A processing means for organizing acquired data and generating and displaying responses to the user.

[0568] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0569] Explanation of the program's processing flow

[0570] 1. The user enters their question through the chat interface.

[0571] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0572] 2. The device sends the question to the natural language processing model and sentiment engine.

[0573] The terminal receives the user's question and sends it to the server. The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the inquiry and the user's sentiment.

[0574] 3. The server analyzes the question and retrieves relevant data.

[0575] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0576] 4. The server analyzes the user's emotions using an emotion engine.

[0577] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0578] 5. The server organizes the data and generates a response that takes emotions into account.

[0579] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0580] 6. The server sends a response to the terminal.

[0581] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0582] 7. The user confirms the response.

[0583] The user checks the response displayed in the chat interface through their device. For example, they might see a response like, "Don't worry, B is the top-selling salesperson this month."

[0584] Specific example

[0585] When new employee A enters the question "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server analyzes the question using an NLP model and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Meanwhile, an emotion engine analyzes new employee A's emotions (e.g., nervousness or reassurance). Based on the retrieved data and the emotion analysis results, the server generates a response such as "The top-selling salesperson this month is B." Furthermore, based on the analysis results from the emotion engine, it can create an emotion-sensitive response such as "Don't worry, B is the top-selling salesperson this month." Finally, the device displays this response in the chat interface, allowing new employee A to quickly and appropriately obtain the necessary information.

[0586] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] The user enters a question into the chat interface. For example, they might type, "Who is the top-selling salesperson this month?"

[0590] Step 2:

[0591] The terminal receives the user's question. It sends the received question to the server.

[0592] Step 3:

[0593] The server receives the question data. The server simultaneously sends this data to the natural language processing (NLP) model and the emotion engine.

[0594] Step 4:

[0595] The server uses an NLP model to analyze the question. For example, it extracts important keywords such as "top sales," "this month," and "sales."

[0596] Step 5:

[0597] The server generates queries using the database API based on the extracted keywords. For example, it generates a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0598] Step 6:

[0599] The server sends the generated query to the database API. The database API executes the query and retrieves the relevant data.

[0600] Step 7:

[0601] The database API retrieves data from the database, for example, "Person B is the top-selling salesperson this month." The server receives this data.

[0602] Step 8:

[0603] The server analyzes the user's emotions using an emotion engine. The emotion engine identifies the user's emotions (e.g., relief, tension, anxiety, etc.) from the text.

[0604] Step 9:

[0605] Based on the data acquired by the server and the sentiment analysis results, it generates a response for the user. For example, if it detects that the user is feeling anxious, it will generate a response in the format of, "Don't worry, salesperson B is the top seller this month."

[0606] Step 10:

[0607] The server sends the generated response to the terminal. The terminal receives this response.

[0608] Step 11:

[0609] The terminal displays the response received from the server in the chat interface. The user then reviews this response.

[0610] Step 12:

[0611] Users read the responses displayed in the chat interface through their device. For example, by confirming a response such as, "Don't worry, B is the top-selling salesperson this month," they can quickly and appropriately obtain information.

[0612] (Example 2)

[0613] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0614] Conventional information retrieval systems have struggled to properly analyze user inquiries and efficiently retrieve relevant data. Furthermore, they have been unable to generate responses that take user emotions into account, resulting in a failure to provide users with appropriate and effective information. Especially when inquiries are complex or influenced by user emotions, more advanced analysis and responses are required.

[0615] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0616] In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for obtaining relevant data based on the analysis results via a database API, means for formatting the obtained data into a user-friendly format and generating an answer, means for sending and displaying the generated answer on a terminal, and an emotion engine that recognizes the user's emotions and reflects them in the analysis results. This makes it possible to provide appropriate information that takes into account not only the user's inquiry but also their emotions.

[0617] A "natural language processing model" is an algorithm that analyzes user inquiries and extracts important keywords and meanings.

[0618] A "database API" is an interface for accessing a database and retrieving necessary data.

[0619] An "emotion engine" is a system that recognizes emotions from the content of a user's inquiry and reflects them in the analysis results.

[0620] A "chat interface" is an interactive input method that allows users to enter inquiries using natural language.

[0621] "Analysis results" refer to the meaning and emotions behind user inquiries, as analyzed by natural language processing models and emotion engines.

[0622] "Related data" refers to information related to the user's inquiry, obtained through the database API.

[0623] A "response generation method" refers to a method of generating content to respond to the user based on the analysis results.

[0624] "Display means" refers to methods or systems for visually providing the generated response to the user.

[0625] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0626] System Overview

[0627] This system consists of the following main components:

[0628] A terminal equipped with a chat interface for users to enter questions.

[0629] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0630] Database API for retrieving related data from a database

[0631] A processing means for organizing acquired data and generating and displaying responses to the user.

[0632] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0633] Program processing flow

[0634] The user uses their device to enter a question into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?" The device receives this question and sends it to the server.

[0635] The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the query content and the user's sentiment. OpenAI's GPT-3 and BERT can be used as natural language processing models for analysis. IBM Watson and Azure Cognitive Services are available as sentiment engines.

[0636] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0637] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0638] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0639] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface. The user checks the response displayed in the chat interface through their terminal.

[0640] Specific example

[0641] A new employee enters the question, "Who is the top-selling salesperson this month?" into the chat interface. The terminal sends this question to the server. The server analyzes the question using an NLP model (e.g., GPT-3) and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Simultaneously, it analyzes the new employee's emotions using an emotion engine (e.g., IBM Watson) and detects anxiety. Based on the retrieved data and the emotion analysis results, the server generates a basic response, "The top-selling salesperson this month is Mr. / Ms. B," and adds supplementary explanations such as "Don't worry." Finally, it sends the response to the terminal, and the new employee can check the response through the chat interface.

[0642] Examples of prompt statements include the following:

[0643] "Who is the top-selling salesperson this month?"

[0644] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0645] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0646] Step 1:

[0647] The user enters a question into the terminal's chat interface. For example, the user might type, "Who is the top-selling salesperson this month?" The input data is the user's inquiry.

[0648] Step 2:

[0649] The terminal receives the user's question and sends it to the server. Specifically, the terminal sends the user's question data to the server using an HTTP request. The input is the question entered by the user, and the output is the question data sent to the server.

[0650] Step 3:

[0651] The server receives the question data and passes it to a natural language processing model for analysis. The server uses an NLP model (e.g., GPT-3) to analyze the intent of the question and extract important keywords (e.g., "top sales," "this month," "sales"). The input is the user's question data, and the output is a list of analyzed keywords.

[0652] Step 4:

[0653] Based on keywords extracted by the server, related data is retrieved using a database API. Specifically, the server queries data related to "the top-selling salesperson this month" via the Salesforce API. The input is a keyword list, and the output is related data retrieved from the database.

[0654] Step 5:

[0655] The server passes the question content to an emotion engine, which analyzes the user's emotions. The emotion engine (e.g., IBM Watson) is used to recognize whether the user is experiencing emotions such as anxiety, joy, or questioning. The input is the user's question data, and the output is the analyzed emotion data.

[0656] Step 6:

[0657] The server generates a response based on relevant data and sentiment analysis results. The server uses an NLG engine to generate an appropriate response based on the acquired data and sentiment analysis results. For example, it might create a response such as, "Don't worry, salesperson B is the top seller this month." The input is relevant data and sentiment data, and the output is the generated response.

[0658] Step 7:

[0659] The server sends the generated response to the terminal. The server sends the response to the terminal as an HTTP response, which the terminal receives and displays to the user. The input is the generated response data, and the output is the response sent to the terminal.

[0660] Step 8:

[0661] The user confirms the response through the chat interface on their device. For example, the user might confirm a response such as, "Don't worry, B is the top salesperson this month." The input is the response data sent from the server, and the output is the response that the user confirms.

[0662] (Application Example 2)

[0663] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0664] Current information management systems in factories often make it difficult for workers to quickly and accurately access the information they need. Furthermore, they fail to consider the emotional state of workers, leading to unclear responses or inappropriate actions. This can reduce work efficiency and increase the likelihood of errors. This invention aims to solve these problems and achieve efficient and appropriate information management.

[0665] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for acquiring relevant data based on the analysis results through a database API, means for formatting the acquired data into a format easily understood by the user and generating an answer, means including an emotion engine that analyzes the user's emotional state and adjusts the answer based on the analysis results, and means for transmitting and displaying the generated answer on a terminal. This makes it possible for workers to quickly and accurately access the information they need and obtain appropriate answers according to their emotional state.

[0666] A "natural language processing model" is an algorithm or machine learning model used to analyze user inquiries.

[0667] A "database API" is an application programming interface that enables access to databases and retrieval of data.

[0668] "Related data" refers to necessary information retrieved from the database based on the user's inquiry.

[0669] "Answer" refers to information provided to the user using the relevant data that has been acquired.

[0670] "Emotional state" refers to the emotional state analyzed from the user's input.

[0671] An "emotion engine" is an engine that analyzes the user's emotional state and adjusts its responses based on the analysis results.

[0672] A "chat interface" is an interface used by users to input their inquiries.

[0673] "Terminal" refers to electronic devices such as computers and mobile devices used by users.

[0674] "Analysis results" refer to the data and information obtained using natural language processing models and database APIs.

[0675] "Formatting" is the process of converting acquired data and information into a format that is easy for users to understand.

[0676] "Means" refers to methods or devices used to achieve a specific function or purpose.

[0677] This invention is a system that streamlines information management within a factory and provides appropriate responses based on the emotional state of workers. Specific embodiments are described below.

[0678] System Overview

[0679] This system consists of the following main components:

[0680] A terminal equipped with a chat interface for users to enter questions.

[0681] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0682] Database API for retrieving related data from a database

[0683] A processing means for organizing acquired data and generating and displaying responses to the user.

[0684] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0685] Hardware and software to use

[0686] Device: A computer or mobile device operated by a user.

[0687] Server: A computer server equipped with high-performance computing resources.

[0688] Natural language processing models: For example, machine learning models such as the BERT model.

[0689] Database: Data management system within a factory (e.g., production planning database)

[0690] Emotion engine: A dedicated library or API for analyzing a user's emotional state (e.g., Sentiment Analysis API).

[0691] Program processing

[0692] The server receives the inquiry entered by the user through the terminal and analyzes the question using a natural language processing model. It extracts important keywords from the analyzed content and retrieves relevant data using a database API. Simultaneously, the emotion engine analyzes the user's emotional state, and based on that information, an optimal response is generated. This ensures that responses are tailored to the user's emotional state.

[0693] Specific examples of the system

[0694] For example, if a new worker asks, "Could you tell me this week's production plan?", the statement is transcribed into text using speech recognition. The server analyzes it using a natural language processing model and an emotion engine, and retrieves relevant production plan data from the database. The final result is displayed as, "Don't worry, this week's production plan is on track," providing the worker with appropriate information.

[0695] Example of a prompt

[0696] The prompt statement is the text input to the generative AI model, and is written as follows:

[0697] "Analyze the following text to identify key keywords (production plan, this week) and the user's sentiment: 'Please tell me this week's production plan.'"

[0698] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0699] Step 1:

[0700] The user enters a question through the chat interface. The input can be in text or voice format. In the case of voice input, speech recognition software converts the speech to text. The entered question (e.g., "Please tell me this week's production plan") is sent from the terminal to the server.

[0701] Step 2:

[0702] The server passes the received question to a natural language processing (NLP) model. The NLP model analyzes the question and extracts key keywords (e.g., "this week," "production plan"). This analysis uses machine learning algorithms to understand the context of the text and grasp the user's intent. The analysis results in the extracted keywords.

[0703] Step 3:

[0704] The server calls a database API based on the analysis results to retrieve relevant data. The server generates a query containing keywords and sends it to the database. The database searches based on the query and returns the corresponding production plan data. The retrieved data (e.g., details of this week's production plan) is returned to the server.

[0705] Step 4:

[0706] The server uses an emotion engine to analyze the user's emotional state. The input question text is passed to the emotion engine, which identifies the corresponding emotion (e.g., reassurance, anxiety, excitement) from the text. The emotion engine then uses an emotion analysis algorithm to evaluate the user's emotional state. The analysis results in the user's emotional information.

[0707] Step 5:

[0708] The server integrates acquired data with sentiment analysis results to generate appropriate responses for the user. A data formatting algorithm is used to transform production plan data into a user-friendly format. The response is adjusted according to the user's emotional state to create an emotionally sensitive message (e.g., "Don't worry, this week's production plan is on track"). The generated response is stored on the server.

[0709] Step 6:

[0710] The server sends the generated response to the device. The device then displays the response again in the chat interface. This allows the user to quickly and appropriately obtain the necessary information. After the response is displayed, the user can take the next action based on the information.

[0711] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0712] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0713] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0714] [Third Embodiment]

[0715] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0716] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0717] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0718] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0719] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0720] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0721] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0722] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0723] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0724] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0725] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0726] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0727] This invention relates to a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0728] System Overview

[0729] This system consists of the following main components:

[0730] A terminal equipped with a chat interface for users to enter questions.

[0731] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0732] A database API for retrieving relevant data from a database (e.g., an internal corporate database) based on a question.

[0733] A processing means for organizing acquired data and generating and displaying responses to the user.

[0734] Explanation of the program's processing flow

[0735] 1. The user enters their question through the chat interface.

[0736] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0737] 2. The device sends the question to the natural language processing model.

[0738] The terminal receives the user's question and sends it to the server. The server then passes this question to a natural language processing model, which parses the query.

[0739] 3. The server analyzes the question and retrieves relevant data.

[0740] The server uses a natural language processing model to analyze the intent behind the user's question. This analysis identifies data related to the question (e.g., "top sales," "this month," "sales," etc.). Next, the server uses a database API to retrieve the relevant data from a database such as Salesforce.

[0741] 4. The server organizes the data and generates a response.

[0742] The server organizes the acquired data and formats it into a user-friendly format. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0743] 5. The server sends a response to the terminal.

[0744] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0745] 6. The user confirms the response.

[0746] Users can view the responses displayed in the chat interface through their device.

[0747] Specific example

[0748] When new employee A types "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server uses a natural language processing model to analyze the question and identify keywords such as "top-selling," "this month," and "salesperson." Next, the server uses the Salesforce database API to retrieve the sales data for this month. Based on this data, it generates a response, "The top-selling salesperson this month is B," and sends it to the device. Finally, the device displays this response in the chat interface, allowing new employee A to quickly obtain the necessary information.

[0749] This system allows companies to efficiently utilize internal information and enables new and mid-career employees to quickly access the information they need. Furthermore, it promotes information sharing and contributes to improved operational efficiency.

[0750] The following describes the processing flow.

[0751] Step 1:

[0752] The user enters a question into the chat interface. For example, they might enter the question, "Who is the top-selling salesperson this month?"

[0753] Step 2:

[0754] The terminal receives the user's question. The terminal sends the question data to the server.

[0755] Step 3:

[0756] The server receives the question data. The server inputs that question data into a natural language processing (NLP) model.

[0757] Step 4:

[0758] The server uses an NLP model to analyze the question. As a result of the analysis, it extracts important keywords contained in the question (e.g., "top sales," "this month," "sales").

[0759] Step 5:

[0760] The server generates queries using the database API based on the extracted keywords. For example, it might generate a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0761] Step 6:

[0762] The server generates a query and sends it to the database API. The database API then executes that query against the database (e.g., Salesforce).

[0763] Step 7:

[0764] The database API retrieves relevant data from the database. For example, it retrieves data indicating that the top-selling salesperson is "Mr. B".

[0765] Step 8:

[0766] The server receives the data it has acquired. Based on that data, the server generates a response for the user. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0767] Step 9:

[0768] The server sends the generated response to the terminal.

[0769] Step 10:

[0770] The device displays the response received from the server in the chat interface.

[0771] Step 11:

[0772] The user checks the response displayed through the chat interface on their device. For example, they might read the response, "This month's top salesperson is Mr. / Ms. B."

[0773] (Example 1)

[0774] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0775] Traditional inquiry systems made it difficult for users to quickly access the information they needed, and especially when dealing with large amounts of data within a company, there was a problem of the significant time it took to search for and retrieve information. Furthermore, they lacked the ability to properly interpret natural language inquiries and provide answers in a user-friendly format, resulting in poor user convenience.

[0776] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0777] In this invention, the server includes means for using a natural language processing model to analyze queries, means for using a database interface to acquire data based on the analysis results, and means for formatting the acquired data into a user-friendly format to generate a response. This makes it possible to quickly and accurately analyze the content of queries entered by users in natural language, efficiently acquire related data, and provide responses in an easy-to-understand format.

[0778] A "natural language processing model for analyzing queries" refers to algorithms and technologies that analyze the content of queries entered by users in natural language and understand their intent and meaning.

[0779] A "database interface for retrieving data" is a software component used to retrieve necessary information from a database, and it has the functionality to communicate with the database through APIs and queries.

[0780] "Means of formatting data into a user-friendly format and generating responses" refers to the processing and technologies used to organize acquired data in a way that is easily understandable to users and to display it in an appropriate manner.

[0781] A "user terminal" is a device used by a user to access the system and input / confirm their inquiry details, and includes personal computers, smartphones, tablets, and other similar devices.

[0782] This invention relates to a system that allows users to quickly access information within a company. This system consists of user terminals, servers, and database APIs as its main components.

[0783] System Configuration

[0784] This system consists of the following main components:

[0785] 1. User Terminal: Equipped with a chat interface for users to input their inquiries. User terminals can be a wide variety of devices, including personal computers, smartphones, and tablets.

[0786] 2. Server: Receives user queries and performs analysis using a natural language processing model. The server understands the intent of the query and retrieves the necessary data via a database API based on that understanding.

[0787] 3. Database API: A software component for accessing an internal enterprise database and retrieving data based on a specified query.

[0788] Program operation

[0789] 1. The user enters a question into the chat interface.

[0790] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0791] 2. The device sends the question to the natural language processing model.

[0792] The terminal sends the received question to the server. After receiving the question, the server passes it to a natural language processing model for analysis.

[0793] 3. The server analyzes the question and retrieves relevant data.

[0794] The server analyzes the question using a natural language processing model (e.g., GPT-3). This analysis identifies keywords such as "top sales," "this month," and "sales." Based on these keywords, the server uses a database API to retrieve relevant data from the company's internal database.

[0795] 4. The server organizes the data and generates a response.

[0796] The server organizes the acquired data and formats it into a user-friendly format. For example, it generates specific answers such as, "This month's top salesperson is Mr. / Ms. B."

[0797] 5. The server sends a response to the terminal.

[0798] The server sends the generated response to the terminal. The terminal displays the response in the chat interface.

[0799] 6. The user confirms the response.

[0800] The user checks the response displayed in the chat interface through their device.

[0801] Specific examples of hardware and software to be used

[0802] Hardware: User devices such as personal computers, smartphones, and tablets.

[0803] Software: Natural language processing models (e.g., GPT-3), database APIs (e.g., Salesforce API), chat interfaces, etc.

[0804] Specific example

[0805] If new employee A enters "Who is the top-selling salesperson this month?", the following steps will be executed.

[0806] 1. The user terminal sends the question to the server.

[0807] 2. The server uses a natural language processing model to analyze the question and identify keywords such as "top sales," "this month," and "sales."

[0808] 3. The server uses the database API to retrieve this month's sales data.

[0809] 4. The server organizes the acquired data and generates a response stating, "This month's top-selling salesperson is Mr. / Ms. B."

[0810] 5. The device receives a response from the server and displays it in the chat interface.

[0811] 6. The user confirms the response.

[0812] Example of a prompt

[0813] "Who is the top-selling salesperson this month?"

[0814] This system enables quick and efficient searching and retrieval of necessary information within a company, improving convenience for users.

[0815] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0816] Specific processing steps of the program for this system

[0817] Step 1:

[0818] The user enters a question into the chat interface.

[0819] Input: Users enter their questions in natural language into the chat interface. Example: "Who is the top-selling salesperson this month?"

[0820] Operation: The terminal receives the text entered by the user and temporarily stores it in an internal buffer.

[0821] Output: Text data of the saved questions.

[0822] Step 2:

[0823] The device sends the question to the natural language processing model.

[0824] Input: Text data of the saved question.

[0825] Operation: The terminal uses an HTTP POST request to send the question text to the server.

[0826] Output: Request data of the question text sent to the server.

[0827] Step 3:

[0828] The server analyzes the question and extracts relevant keywords.

[0829] Input: Request data of the question text received from the terminal.

[0830] Operation: The server uses a natural language processing model (e.g., GPT-3) to analyze the question text. Through this analysis, keywords such as "top sales," "this month," and "sales" are extracted.

[0831] Output: Extracted keyword data.

[0832] Step 4:

[0833] The server retrieves relevant data from the database.

[0834] Input: Extracted keyword data.

[0835] Operation: The server uses a database API (e.g., an enterprise database API) to generate keyword-based queries and retrieve relevant data from a database such as Salesforce.

[0836] Output: The retrieved related data.

[0837] Step 5:

[0838] The server organizes the data and generates a response.

[0839] Input: The retrieved related data.

[0840] Operation: The server analyzes and organizes the acquired data and generates a response in a format that is easy for the user to understand. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[0841] Output: Organized response data.

[0842] Step 6:

[0843] The server sends a response to the terminal.

[0844] Input: Organized response data.

[0845] Operation: The server encodes the response data in JSON format and sends it to the terminal as an HTTP response.

[0846] Output: Response data sent to the terminal.

[0847] Step 7:

[0848] The device displays the reply in the chat interface.

[0849] Input: Response data sent to the terminal.

[0850] Operation: The device analyzes the received response data and displays it in the chat interface.

[0851] Output: The response displayed in the chat interface.

[0852] Step 8:

[0853] The user confirms the response.

[0854] Input: The response displayed in the chat interface.

[0855] Operation: The user checks the response displayed in the device's chat interface.

[0856] Output: The response confirmed by the user.

[0857] Through these steps, the system can analyze user inquiries in natural language, quickly and efficiently retrieve the necessary data, and provide clear and understandable answers.

[0858] (Application Example 1)

[0859] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0860] In logistics centers, there is a problem where staff have difficulty quickly obtaining necessary information, leading to decreased operational efficiency. Furthermore, the lack of real-time information access makes it difficult to respond quickly on-site.

[0861] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0862] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for acquiring relevant data based on the analysis results via a database API, means for formatting the acquired data into a user-friendly format and generating a response, means for sending and displaying the generated response on a terminal, and means for enabling users to check logistics-related information in real time via an interface. This allows staff to easily acquire necessary information, improve operational efficiency, and enable rapid, real-time responses.

[0863] A "natural language processing model" is a machine learning algorithm used to understand and analyze natural language.

[0864] "User inquiries" refer to questions and requests that users enter into the system.

[0865] A "database API" is an interface that allows different software systems to exchange data with each other.

[0866] "Related data" refers to information that the server needs to identify and retrieve in response to a user's inquiry.

[0867] A "response" is the result of providing information generated in response to a user's inquiry.

[0868] A "device" refers to a device used by a user, such as a smartphone, smart glasses, or computer.

[0869] "Logistics-related information" refers to data related to logistics center operations, such as inventory status, shipping status, receiving status, and delivery status.

[0870] "Real-time" refers to processing and data updates that occur almost simultaneously.

[0871] An "interface" is a means or method for exchanging information between a user and a system.

[0872] This invention is a system for improving information acquisition and operational efficiency in logistics centers. This system is implemented by integrating a natural language processing model, a database API, and a chat interface.

[0873] Hardware and software to be used

[0874] Hardware: Smartphones, smart glasses, servers

[0875] Software: Chat interface, natural language processing models (e.g., GPT-4), database APIs (e.g., SQL-based inventory management systems)

[0876] System Configuration

[0877] 1. User inquiry input

[0878] Users (for example, staff at a logistics center) enter work-related questions using a chat interface on their smartphone or smart glasses. For example, they might ask questions like the following:

[0879] "What is the shipping status for today?"

[0880] "Please tell me the current stock level."

[0881] 2. Natural Language Processing and Data Acquisition

[0882] The terminal sends the user's question to the server. The server uses a natural language processing model (e.g., GPT-4) to analyze the user's inquiry. This analysis identifies relevant keywords (e.g., "shipping status," "inventory level"). Next, the server uses a database API to retrieve the necessary information from a database related to the logistics center (e.g., a SQL-based inventory management system).

[0883] 3. Answer generation and display

[0884] The server organizes the retrieved data and formats it into a user-friendly format. For example, if information about shipping status is retrieved, it might be formatted as "Today's shipping status is as follows." The generated response is then sent back to the terminal and displayed in the user's chat interface.

[0885] Specific example

[0886] For example, if a staff member at a logistics center wants to check the inventory count using smart glasses, they would input a prompt message like the following into the AI ​​model that generates the inventory:

[0887] Example of a prompt

[0888] User question: "What is the current stock level?"

[0889] Answer: "We currently have 120 units left in stock."

[0890] Please identify the relevant data.

[0891] By using this prompt, the natural language processing model identifies the "inventory quantity," generates an appropriate database query to retrieve the inventory quantity, and then generates and displays the final response. This allows for more efficient operations at the logistics center and enables real-time information access.

[0892] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0893] Step 1:

[0894] The user enters their inquiry into the chat interface using a device (smartphone or smart glasses). For example, they might enter the question, "What is the current stock quantity?" This input is stored on the device in text format.

[0895] Step 2:

[0896] The terminal sends the entered query content to the server. Metadata such as the user ID and timestamp are also sent along with it. This input data is received by the server and passed on to the next processing step.

[0897] Step 3:

[0898] The server passes the received query content to a natural language processing model (e.g., GPT-4) for analysis. Specifically, it extracts relevant keywords (e.g., "inventory quantity") from the query content and understands the intent. This process identifies the type of data that should be retrieved. The output consists of the identified keywords and intent.

[0899] Step 4:

[0900] The server calls a database API based on identified keywords and intents to retrieve relevant data. For example, to retrieve data about "inventory levels," it sends a query to a SQL-based inventory management system. The input is the identified keywords, and the output is inventory level data as the query result.

[0901] Step 5:

[0902] The server formats the retrieved data into a format that is easy for the user to understand. Specifically, it converts the retrieved inventory data into a format such as "Current inventory: 120 units remaining." At this stage, the input is the raw query result data, and the output is formatted text data.

[0903] Step 6:

[0904] The server sends the generated response to the terminal. The terminal displays the received response in the chat interface. This allows the user to quickly obtain the necessary information. In this final step, the input is the formatted response text, and the output is the information displayed on the user's terminal.

[0905] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0906] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0907] System Overview

[0908] This system consists of the following main components:

[0909] A terminal equipped with a chat interface for users to enter questions.

[0910] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0911] Database API for retrieving related data from a database

[0912] A processing means for organizing acquired data and generating and displaying responses to the user.

[0913] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0914] Explanation of the program's processing flow

[0915] 1. The user enters their question through the chat interface.

[0916] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[0917] 2. The device sends the question to the natural language processing model and sentiment engine.

[0918] The terminal receives the user's question and sends it to the server. The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the inquiry and the user's sentiment.

[0919] 3. The server analyzes the question and retrieves relevant data.

[0920] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0921] 4. The server analyzes the user's emotions using an emotion engine.

[0922] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0923] 5. The server organizes the data and generates a response that takes emotions into account.

[0924] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0925] 6. The server sends a response to the terminal.

[0926] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[0927] 7. The user confirms the response.

[0928] The user checks the response displayed in the chat interface through their device. For example, they might see a response like, "Don't worry, B is the top-selling salesperson this month."

[0929] Specific example

[0930] When new employee A enters the question "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server analyzes the question using an NLP model and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Meanwhile, an emotion engine analyzes new employee A's emotions (e.g., nervousness or reassurance). Based on the retrieved data and the emotion analysis results, the server generates a response such as "The top-selling salesperson this month is B." Furthermore, based on the analysis results from the emotion engine, it can create an emotion-sensitive response such as "Don't worry, B is the top-selling salesperson this month." Finally, the device displays this response in the chat interface, allowing new employee A to quickly and appropriately obtain the necessary information.

[0931] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0932] The following describes the processing flow.

[0933] Step 1:

[0934] The user enters a question into the chat interface. For example, they might type, "Who is the top-selling salesperson this month?"

[0935] Step 2:

[0936] The terminal receives the user's question. It sends the received question to the server.

[0937] Step 3:

[0938] The server receives the question data. The server simultaneously sends this data to the natural language processing (NLP) model and the emotion engine.

[0939] Step 4:

[0940] The server uses an NLP model to analyze the question. For example, it extracts important keywords such as "top sales," "this month," and "sales."

[0941] Step 5:

[0942] The server generates queries using the database API based on the extracted keywords. For example, it generates a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[0943] Step 6:

[0944] The server sends the generated query to the database API. The database API executes the query and retrieves the relevant data.

[0945] Step 7:

[0946] The database API retrieves data from the database, for example, "Person B is the top-selling salesperson this month." The server receives this data.

[0947] Step 8:

[0948] The server analyzes the user's emotions using an emotion engine. The emotion engine identifies the user's emotions (e.g., relief, tension, anxiety, etc.) from the text.

[0949] Step 9:

[0950] Based on the data acquired by the server and the sentiment analysis results, it generates a response for the user. For example, if it detects that the user is feeling anxious, it will generate a response in the format of, "Don't worry, salesperson B is the top seller this month."

[0951] Step 10:

[0952] The server sends the generated response to the terminal. The terminal receives this response.

[0953] Step 11:

[0954] The terminal displays the response received from the server in the chat interface. The user then reviews this response.

[0955] Step 12:

[0956] Users read the responses displayed in the chat interface through their device. For example, by confirming a response such as, "Don't worry, B is the top-selling salesperson this month," they can quickly and appropriately obtain information.

[0957] (Example 2)

[0958] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0959] Conventional information retrieval systems have struggled to properly analyze user inquiries and efficiently retrieve relevant data. Furthermore, they have been unable to generate responses that take user emotions into account, resulting in a failure to provide users with appropriate and effective information. Especially when inquiries are complex or influenced by user emotions, more advanced analysis and responses are required.

[0960] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0961] In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for obtaining relevant data based on the analysis results via a database API, means for formatting the obtained data into a user-friendly format and generating an answer, means for sending and displaying the generated answer on a terminal, and an emotion engine that recognizes the user's emotions and reflects them in the analysis results. This makes it possible to provide appropriate information that takes into account not only the user's inquiry but also their emotions.

[0962] A "natural language processing model" is an algorithm that analyzes user inquiries and extracts important keywords and meanings.

[0963] A "database API" is an interface for accessing a database and retrieving necessary data.

[0964] An "emotion engine" is a system that recognizes emotions from the content of a user's inquiry and reflects them in the analysis results.

[0965] A "chat interface" is an interactive input method that allows users to enter inquiries using natural language.

[0966] "Analysis results" refer to the meaning and emotions behind user inquiries, as analyzed by natural language processing models and emotion engines.

[0967] "Related data" refers to information related to the user's inquiry, obtained through the database API.

[0968] A "response generation method" refers to a method of generating content to respond to the user based on the analysis results.

[0969] "Display means" refers to methods or systems for visually providing the generated response to the user.

[0970] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[0971] System Overview

[0972] This system consists of the following main components:

[0973] A terminal equipped with a chat interface for users to enter questions.

[0974] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[0975] Database API for retrieving related data from a database

[0976] A processing means for organizing acquired data and generating and displaying responses to the user.

[0977] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[0978] Program processing flow

[0979] The user uses their device to enter a question into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?" The device receives this question and sends it to the server.

[0980] The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the query content and the user's sentiment. OpenAI's GPT-3 and BERT can be used as natural language processing models for analysis. IBM Watson and Azure Cognitive Services are available as sentiment engines.

[0981] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[0982] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[0983] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[0984] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface. The user checks the response displayed in the chat interface through their terminal.

[0985] Specific example

[0986] A new employee enters the question, "Who is the top-selling salesperson this month?" into the chat interface. The terminal sends this question to the server. The server analyzes the question using an NLP model (e.g., GPT-3) and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Simultaneously, it analyzes the new employee's emotions using an emotion engine (e.g., IBM Watson) and detects anxiety. Based on the retrieved data and the emotion analysis results, the server generates a basic response, "The top-selling salesperson this month is Mr. / Ms. B," and adds supplementary explanations such as "Don't worry." Finally, it sends the response to the terminal, and the new employee can check the response through the chat interface.

[0987] Examples of prompt statements include the following:

[0988] "Who is the top-selling salesperson this month?"

[0989] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[0990] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0991] Step 1:

[0992] The user enters a question into the terminal's chat interface. For example, the user might type, "Who is the top-selling salesperson this month?" The input data is the user's inquiry.

[0993] Step 2:

[0994] The terminal receives the user's question and sends it to the server. Specifically, the terminal sends the user's question data to the server using an HTTP request. The input is the question entered by the user, and the output is the question data sent to the server.

[0995] Step 3:

[0996] The server receives the question data and passes it to a natural language processing model for analysis. The server uses an NLP model (e.g., GPT-3) to analyze the intent of the question and extract important keywords (e.g., "top sales," "this month," "sales"). The input is the user's question data, and the output is a list of analyzed keywords.

[0997] Step 4:

[0998] Based on keywords extracted by the server, related data is retrieved using a database API. Specifically, the server queries data related to "the top-selling salesperson this month" via the Salesforce API. The input is a keyword list, and the output is related data retrieved from the database.

[0999] Step 5:

[1000] The server passes the question content to an emotion engine, which analyzes the user's emotions. The emotion engine (e.g., IBM Watson) is used to recognize whether the user is experiencing emotions such as anxiety, joy, or questioning. The input is the user's question data, and the output is the analyzed emotion data.

[1001] Step 6:

[1002] The server generates a response based on relevant data and sentiment analysis results. The server uses an NLG engine to generate an appropriate response based on the acquired data and sentiment analysis results. For example, it might create a response such as, "Don't worry, salesperson B is the top seller this month." The input is relevant data and sentiment data, and the output is the generated response.

[1003] Step 7:

[1004] The server sends the generated response to the terminal. The server sends the response to the terminal as an HTTP response, which the terminal receives and displays to the user. The input is the generated response data, and the output is the response sent to the terminal.

[1005] Step 8:

[1006] The user confirms the response through the chat interface on their device. For example, the user might confirm a response such as, "Don't worry, B is the top salesperson this month." The input is the response data sent from the server, and the output is the response that the user confirms.

[1007] (Application Example 2)

[1008] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1009] Current information management systems in factories often make it difficult for workers to quickly and accurately access the information they need. Furthermore, they fail to consider the emotional state of workers, leading to unclear responses or inappropriate actions. This can reduce work efficiency and increase the likelihood of errors. This invention aims to solve these problems and achieve efficient and appropriate information management.

[1010] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for acquiring relevant data based on the analysis results through a database API, means for formatting the acquired data into a format easily understood by the user and generating an answer, means including an emotion engine that analyzes the user's emotional state and adjusts the answer based on the analysis results, and means for transmitting and displaying the generated answer on a terminal. This makes it possible for workers to quickly and accurately access the information they need and obtain appropriate answers according to their emotional state.

[1011] A "natural language processing model" is an algorithm or machine learning model used to analyze user inquiries.

[1012] A "database API" is an application programming interface that enables access to databases and retrieval of data.

[1013] "Related data" refers to necessary information retrieved from the database based on the user's inquiry.

[1014] "Answer" refers to information provided to the user using the relevant data that has been acquired.

[1015] "Emotional state" refers to the emotional state analyzed from the user's input.

[1016] An "emotion engine" is an engine that analyzes the user's emotional state and adjusts its responses based on the analysis results.

[1017] A "chat interface" is an interface used by users to input their inquiries.

[1018] "Terminal" refers to electronic devices such as computers and mobile devices used by users.

[1019] "Analysis results" refer to the data and information obtained using natural language processing models and database APIs.

[1020] "Formatting" is the process of converting acquired data and information into a format that is easy for users to understand.

[1021] "Means" refers to methods or devices used to achieve a specific function or purpose.

[1022] This invention is a system that streamlines information management within a factory and provides appropriate responses based on the emotional state of workers. Specific embodiments are described below.

[1023] System Overview

[1024] This system consists of the following main components:

[1025] A terminal equipped with a chat interface for users to enter questions.

[1026] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[1027] Database API for retrieving related data from a database

[1028] A processing means for organizing acquired data and generating and displaying responses to the user.

[1029] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[1030] Hardware and software to use

[1031] Device: A computer or mobile device operated by a user.

[1032] Server: A computer server equipped with high-performance computing resources.

[1033] Natural language processing models: For example, machine learning models such as the BERT model.

[1034] Database: Data management system within a factory (e.g., production planning database)

[1035] Emotion engine: A dedicated library or API for analyzing a user's emotional state (e.g., Sentiment Analysis API).

[1036] Program processing

[1037] The server receives the inquiry entered by the user through the terminal and analyzes the question using a natural language processing model. It extracts important keywords from the analyzed content and retrieves relevant data using a database API. Simultaneously, the emotion engine analyzes the user's emotional state, and based on that information, an optimal response is generated. This ensures that responses are tailored to the user's emotional state.

[1038] Specific examples of the system

[1039] For example, if a new worker asks, "Could you tell me this week's production plan?", the statement is transcribed into text using speech recognition. The server analyzes it using a natural language processing model and an emotion engine, and retrieves relevant production plan data from the database. The final result is displayed as, "Don't worry, this week's production plan is on track," providing the worker with appropriate information.

[1040] Example of a prompt

[1041] The prompt statement is the text input to the generative AI model, and is written as follows:

[1042] "Analyze the following text to identify key keywords (production plan, this week) and the user's sentiment: 'Please tell me this week's production plan.'"

[1043] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1044] Step 1:

[1045] The user enters a question through the chat interface. The input can be in text or voice format. In the case of voice input, speech recognition software converts the speech to text. The entered question (e.g., "Please tell me this week's production plan") is sent from the terminal to the server.

[1046] Step 2:

[1047] The server passes the received question to a natural language processing (NLP) model. The NLP model analyzes the question and extracts key keywords (e.g., "this week," "production plan"). This analysis uses machine learning algorithms to understand the context of the text and grasp the user's intent. The analysis results in the extracted keywords.

[1048] Step 3:

[1049] The server calls a database API based on the analysis results to retrieve relevant data. The server generates a query containing keywords and sends it to the database. The database searches based on the query and returns the corresponding production plan data. The retrieved data (e.g., details of this week's production plan) is returned to the server.

[1050] Step 4:

[1051] The server uses an emotion engine to analyze the user's emotional state. The input question text is passed to the emotion engine, which identifies the corresponding emotion (e.g., reassurance, anxiety, excitement) from the text. The emotion engine then uses an emotion analysis algorithm to evaluate the user's emotional state. The analysis results in the user's emotional information.

[1052] Step 5:

[1053] The server integrates acquired data with sentiment analysis results to generate appropriate responses for the user. A data formatting algorithm is used to transform production plan data into a user-friendly format. The response is adjusted according to the user's emotional state to create an emotionally sensitive message (e.g., "Don't worry, this week's production plan is on track"). The generated response is stored on the server.

[1054] Step 6:

[1055] The server sends the generated response to the device. The device then displays the response again in the chat interface. This allows the user to quickly and appropriately obtain the necessary information. After the response is displayed, the user can take the next action based on the information.

[1056] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1057] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1058] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1059] [Fourth Embodiment]

[1060] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1061] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1062] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1063] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1064] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1065] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1066] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1067] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1068] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1069] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1070] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1071] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1072] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1073] This invention relates to a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[1074] System Overview

[1075] This system consists of the following main components:

[1076] A terminal equipped with a chat interface for users to enter questions.

[1077] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[1078] A database API for retrieving relevant data from a database (e.g., an internal corporate database) based on a question.

[1079] A processing means for organizing acquired data and generating and displaying responses to the user.

[1080] Explanation of the program's processing flow

[1081] 1. The user enters their question through the chat interface.

[1082] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[1083] 2. The device sends the question to the natural language processing model.

[1084] The terminal receives the user's question and sends it to the server. The server then passes this question to a natural language processing model, which parses the query.

[1085] 3. The server analyzes the question and retrieves relevant data.

[1086] The server uses a natural language processing model to analyze the intent behind the user's question. This analysis identifies data related to the question (e.g., "top sales," "this month," "sales," etc.). Next, the server uses a database API to retrieve the relevant data from a database such as Salesforce.

[1087] 4. The server organizes the data and generates a response.

[1088] The server organizes the acquired data and formats it into a user-friendly format. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[1089] 5. The server sends a response to the terminal.

[1090] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[1091] 6. The user confirms the response.

[1092] Users can view the responses displayed in the chat interface through their device.

[1093] Specific example

[1094] When new employee A types "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server uses a natural language processing model to analyze the question and identify keywords such as "top-selling," "this month," and "salesperson." Next, the server uses the Salesforce database API to retrieve the sales data for this month. Based on this data, it generates a response, "The top-selling salesperson this month is B," and sends it to the device. Finally, the device displays this response in the chat interface, allowing new employee A to quickly obtain the necessary information.

[1095] This system allows companies to efficiently utilize internal information and enables new and mid-career employees to quickly access the information they need. Furthermore, it promotes information sharing and contributes to improved operational efficiency.

[1096] The following describes the processing flow.

[1097] Step 1:

[1098] The user enters a question into the chat interface. For example, they might enter the question, "Who is the top-selling salesperson this month?"

[1099] Step 2:

[1100] The terminal receives the user's question. The terminal sends the question data to the server.

[1101] Step 3:

[1102] The server receives the question data. The server inputs that question data into a natural language processing (NLP) model.

[1103] Step 4:

[1104] The server uses an NLP model to analyze the question. As a result of the analysis, it extracts important keywords contained in the question (e.g., "top sales," "this month," "sales").

[1105] Step 5:

[1106] The server generates queries using the database API based on the extracted keywords. For example, it might generate a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[1107] Step 6:

[1108] The server generates a query and sends it to the database API. The database API then executes that query against the database (e.g., Salesforce).

[1109] Step 7:

[1110] The database API retrieves relevant data from the database. For example, it retrieves data indicating that the top-selling salesperson is "Mr. B".

[1111] Step 8:

[1112] The server receives the data it has acquired. Based on that data, the server generates a response for the user. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[1113] Step 9:

[1114] The server sends the generated response to the terminal.

[1115] Step 10:

[1116] The device displays the response received from the server in the chat interface.

[1117] Step 11:

[1118] The user checks the response displayed through the chat interface on their device. For example, they might read the response, "This month's top salesperson is Mr. / Ms. B."

[1119] (Example 1)

[1120] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1121] Traditional inquiry systems made it difficult for users to quickly access the information they needed, and especially when dealing with large amounts of data within a company, there was a problem of the significant time it took to search for and retrieve information. Furthermore, they lacked the ability to properly interpret natural language inquiries and provide answers in a user-friendly format, resulting in poor user convenience.

[1122] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1123] In this invention, the server includes means for using a natural language processing model to analyze queries, means for using a database interface to acquire data based on the analysis results, and means for formatting the acquired data into a user-friendly format to generate a response. This makes it possible to quickly and accurately analyze the content of queries entered by users in natural language, efficiently acquire related data, and provide responses in an easy-to-understand format.

[1124] A "natural language processing model for analyzing queries" refers to algorithms and technologies that analyze the content of queries entered by users in natural language and understand their intent and meaning.

[1125] A "database interface for retrieving data" is a software component used to retrieve necessary information from a database, and it has the functionality to communicate with the database through APIs and queries.

[1126] "Means of formatting data into a user-friendly format and generating responses" refers to the processing and technologies used to organize acquired data in a way that is easily understandable to users and to display it in an appropriate manner.

[1127] A "user terminal" is a device used by a user to access the system and input / confirm their inquiry details, and includes personal computers, smartphones, tablets, and other similar devices.

[1128] This invention relates to a system that allows users to quickly access information within a company. This system consists of user terminals, servers, and database APIs as its main components.

[1129] System Configuration

[1130] This system consists of the following main components:

[1131] 1. User Terminal: Equipped with a chat interface for users to input their inquiries. User terminals can be a wide variety of devices, including personal computers, smartphones, and tablets.

[1132] 2. Server: Receives user queries and performs analysis using a natural language processing model. The server understands the intent of the query and retrieves the necessary data via a database API based on that understanding.

[1133] 3. Database API: A software component for accessing an internal enterprise database and retrieving data based on a specified query.

[1134] Program operation

[1135] 1. The user enters a question into the chat interface.

[1136] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[1137] 2. The device sends the question to the natural language processing model.

[1138] The terminal sends the received question to the server. After receiving the question, the server passes it to a natural language processing model for analysis.

[1139] 3. The server analyzes the question and retrieves relevant data.

[1140] The server analyzes the question using a natural language processing model (e.g., GPT-3). This analysis identifies keywords such as "top sales," "this month," and "sales." Based on these keywords, the server uses a database API to retrieve relevant data from the company's internal database.

[1141] 4. The server organizes the data and generates a response.

[1142] The server organizes the acquired data and formats it into a user-friendly format. For example, it generates specific answers such as, "This month's top salesperson is Mr. / Ms. B."

[1143] 5. The server sends a response to the terminal.

[1144] The server sends the generated response to the terminal. The terminal displays the response in the chat interface.

[1145] 6. The user confirms the response.

[1146] The user checks the response displayed in the chat interface through their device.

[1147] Specific examples of hardware and software to be used

[1148] Hardware: User devices such as personal computers, smartphones, and tablets.

[1149] Software: Natural language processing models (e.g., GPT-3), database APIs (e.g., Salesforce API), chat interfaces, etc.

[1150] Specific example

[1151] If new employee A enters "Who is the top-selling salesperson this month?", the following steps will be executed.

[1152] 1. The user terminal sends the question to the server.

[1153] 2. The server uses a natural language processing model to analyze the question and identify keywords such as "top sales," "this month," and "sales."

[1154] 3. The server uses the database API to retrieve this month's sales data.

[1155] 4. The server organizes the acquired data and generates a response stating, "This month's top-selling salesperson is Mr. / Ms. B."

[1156] 5. The device receives a response from the server and displays it in the chat interface.

[1157] 6. The user confirms the response.

[1158] Example of a prompt

[1159] "Who is the top-selling salesperson this month?"

[1160] This system enables quick and efficient searching and retrieval of necessary information within a company, improving convenience for users.

[1161] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1162] Specific processing steps of the program for this system

[1163] Step 1:

[1164] The user enters a question into the chat interface.

[1165] Input: Users enter their questions in natural language into the chat interface. Example: "Who is the top-selling salesperson this month?"

[1166] Operation: The terminal receives the text entered by the user and temporarily stores it in an internal buffer.

[1167] Output: Text data of the saved questions.

[1168] Step 2:

[1169] The device sends the question to the natural language processing model.

[1170] Input: Text data of the saved question.

[1171] Operation: The terminal uses an HTTP POST request to send the question text to the server.

[1172] Output: Request data of the question text sent to the server.

[1173] Step 3:

[1174] The server analyzes the question and extracts relevant keywords.

[1175] Input: Request data of the question text received from the terminal.

[1176] Operation: The server uses a natural language processing model (e.g., GPT-3) to analyze the question text. Through this analysis, keywords such as "top sales," "this month," and "sales" are extracted.

[1177] Output: Extracted keyword data.

[1178] Step 4:

[1179] The server retrieves relevant data from the database.

[1180] Input: Extracted keyword data.

[1181] Operation: The server uses a database API (e.g., an enterprise database API) to generate keyword-based queries and retrieve relevant data from a database such as Salesforce.

[1182] Output: The retrieved related data.

[1183] Step 5:

[1184] The server organizes the data and generates a response.

[1185] Input: The retrieved related data.

[1186] Operation: The server analyzes and organizes the acquired data and generates a response in a format that is easy for the user to understand. For example, it might generate a response such as, "This month's top salesperson is Mr. / Ms. B."

[1187] Output: Organized response data.

[1188] Step 6:

[1189] The server sends a response to the terminal.

[1190] Input: Organized response data.

[1191] Operation: The server encodes the response data in JSON format and sends it to the terminal as an HTTP response.

[1192] Output: Response data sent to the terminal.

[1193] Step 7:

[1194] The device displays the reply in the chat interface.

[1195] Input: Response data sent to the terminal.

[1196] Operation: The device analyzes the received response data and displays it in the chat interface.

[1197] Output: The response displayed in the chat interface.

[1198] Step 8:

[1199] The user confirms the response.

[1200] Input: The response displayed in the chat interface.

[1201] Operation: The user checks the response displayed in the device's chat interface.

[1202] Output: The response confirmed by the user.

[1203] Through these steps, the system can analyze user inquiries in natural language, quickly and efficiently retrieve the necessary data, and provide clear and understandable answers.

[1204] (Application Example 1)

[1205] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1206] In logistics centers, there is a problem where staff have difficulty quickly obtaining necessary information, leading to decreased operational efficiency. Furthermore, the lack of real-time information access makes it difficult to respond quickly on-site.

[1207] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1208] In this invention, the server includes means for analyzing user inquiries using a natural language processing model, means for acquiring relevant data based on the analysis results via a database API, means for formatting the acquired data into a user-friendly format and generating a response, means for sending and displaying the generated response on a terminal, and means for enabling users to check logistics-related information in real time via an interface. This allows staff to easily acquire necessary information, improve operational efficiency, and enable rapid, real-time responses.

[1209] A "natural language processing model" is a machine learning algorithm used to understand and analyze natural language.

[1210] "User inquiries" refer to questions and requests that users enter into the system.

[1211] A "database API" is an interface that allows different software systems to exchange data with each other.

[1212] "Related data" refers to information that the server needs to identify and retrieve in response to a user's inquiry.

[1213] A "response" is the result of providing information generated in response to a user's inquiry.

[1214] A "device" refers to a device used by a user, such as a smartphone, smart glasses, or computer.

[1215] "Logistics-related information" refers to data related to logistics center operations, such as inventory status, shipping status, receiving status, and delivery status.

[1216] "Real-time" refers to processing and data updates that occur almost simultaneously.

[1217] An "interface" is a means or method for exchanging information between a user and a system.

[1218] This invention is a system for improving information acquisition and operational efficiency in logistics centers. This system is implemented by integrating a natural language processing model, a database API, and a chat interface.

[1219] Hardware and software to be used

[1220] Hardware: Smartphones, smart glasses, servers

[1221] Software: Chat interface, natural language processing models (e.g., GPT-4), database APIs (e.g., SQL-based inventory management systems)

[1222] System Configuration

[1223] 1. User inquiry input

[1224] Users (for example, staff at a logistics center) enter work-related questions using a chat interface on their smartphone or smart glasses. For example, they might ask questions like the following:

[1225] "What is the shipping status for today?"

[1226] "Please tell me the current stock level."

[1227] 2. Natural Language Processing and Data Acquisition

[1228] The terminal sends the user's question to the server. The server uses a natural language processing model (e.g., GPT-4) to analyze the user's inquiry. This analysis identifies relevant keywords (e.g., "shipping status," "inventory level"). Next, the server uses a database API to retrieve the necessary information from a database related to the logistics center (e.g., a SQL-based inventory management system).

[1229] 3. Answer generation and display

[1230] The server organizes the retrieved data and formats it into a user-friendly format. For example, if information about shipping status is retrieved, it might be formatted as "Today's shipping status is as follows." The generated response is then sent back to the terminal and displayed in the user's chat interface.

[1231] Specific example

[1232] For example, if a staff member at a logistics center wants to check the inventory count using smart glasses, they would input a prompt message like the following into the AI ​​model that generates the inventory:

[1233] Example of a prompt

[1234] User question: "What is the current stock level?"

[1235] Answer: "We currently have 120 units left in stock."

[1236] Please identify the relevant data.

[1237] By using this prompt, the natural language processing model identifies the "inventory quantity," generates an appropriate database query to retrieve the inventory quantity, and then generates and displays the final response. This allows for more efficient operations at the logistics center and enables real-time information access.

[1238] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1239] Step 1:

[1240] The user enters their inquiry into the chat interface using a device (smartphone or smart glasses). For example, they might enter the question, "What is the current stock quantity?" This input is stored on the device in text format.

[1241] Step 2:

[1242] The terminal sends the entered query content to the server. Metadata such as the user ID and timestamp are also sent along with it. This input data is received by the server and passed on to the next processing step.

[1243] Step 3:

[1244] The server passes the received query content to a natural language processing model (e.g., GPT-4) for analysis. Specifically, it extracts relevant keywords (e.g., "inventory quantity") from the query content and understands the intent. This process identifies the type of data that should be retrieved. The output consists of the identified keywords and intent.

[1245] Step 4:

[1246] The server calls a database API based on identified keywords and intents to retrieve relevant data. For example, to retrieve data about "inventory levels," it sends a query to a SQL-based inventory management system. The input is the identified keywords, and the output is inventory level data as the query result.

[1247] Step 5:

[1248] The server formats the retrieved data into a format that is easy for the user to understand. Specifically, it converts the retrieved inventory data into a format such as "Current inventory: 120 units remaining." At this stage, the input is the raw query result data, and the output is formatted text data.

[1249] Step 6:

[1250] The server sends the generated response to the terminal. The terminal displays the received response in the chat interface. This allows the user to quickly obtain the necessary information. In this final step, the input is the formatted response text, and the output is the information displayed on the user's terminal.

[1251] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1252] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[1253] System Overview

[1254] This system consists of the following main components:

[1255] A terminal equipped with a chat interface for users to enter questions.

[1256] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[1257] Database API for retrieving related data from a database

[1258] A processing means for organizing acquired data and generating and displaying responses to the user.

[1259] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[1260] Explanation of the program's processing flow

[1261] 1. The user enters their question through the chat interface.

[1262] Users use their devices to enter questions into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?"

[1263] 2. The device sends the question to the natural language processing model and sentiment engine.

[1264] The terminal receives the user's question and sends it to the server. The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the inquiry and the user's sentiment.

[1265] 3. The server analyzes the question and retrieves relevant data.

[1266] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[1267] 4. The server analyzes the user's emotions using an emotion engine.

[1268] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[1269] 5. The server organizes the data and generates a response that takes emotions into account.

[1270] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[1271] 6. The server sends a response to the terminal.

[1272] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface.

[1273] 7. The user confirms the response.

[1274] The user checks the response displayed in the chat interface through their device. For example, they might see a response like, "Don't worry, B is the top-selling salesperson this month."

[1275] Specific example

[1276] When new employee A enters the question "Who is the top-selling salesperson this month?" into the chat interface, the device sends this question to the server. The server analyzes the question using an NLP model and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Meanwhile, an emotion engine analyzes new employee A's emotions (e.g., nervousness or reassurance). Based on the retrieved data and the emotion analysis results, the server generates a response such as "The top-selling salesperson this month is B." Furthermore, based on the analysis results from the emotion engine, it can create an emotion-sensitive response such as "Don't worry, B is the top-selling salesperson this month." Finally, the device displays this response in the chat interface, allowing new employee A to quickly and appropriately obtain the necessary information.

[1277] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[1278] The following describes the processing flow.

[1279] Step 1:

[1280] The user enters a question into the chat interface. For example, they might type, "Who is the top-selling salesperson this month?"

[1281] Step 2:

[1282] The terminal receives the user's question. It sends the received question to the server.

[1283] Step 3:

[1284] The server receives the question data. The server simultaneously sends this data to the natural language processing (NLP) model and the emotion engine.

[1285] Step 4:

[1286] The server uses an NLP model to analyze the question. For example, it extracts important keywords such as "top sales," "this month," and "sales."

[1287] Step 5:

[1288] The server generates queries using the database API based on the extracted keywords. For example, it generates a query like "SELECT Top_Salesperson FROM SalesData WHERE Month = '2023-10'".

[1289] Step 6:

[1290] The server sends the generated query to the database API. The database API executes the query and retrieves the relevant data.

[1291] Step 7:

[1292] The database API retrieves data from the database, for example, "Person B is the top-selling salesperson this month." The server receives this data.

[1293] Step 8:

[1294] The server analyzes the user's emotions using an emotion engine. The emotion engine identifies the user's emotions (e.g., relief, tension, anxiety, etc.) from the text.

[1295] Step 9:

[1296] Based on the data acquired by the server and the sentiment analysis results, it generates a response for the user. For example, if it detects that the user is feeling anxious, it will generate a response in the format of, "Don't worry, salesperson B is the top seller this month."

[1297] Step 10:

[1298] The server sends the generated response to the terminal. The terminal receives this response.

[1299] Step 11:

[1300] The terminal displays the response received from the server in the chat interface. The user then reviews this response.

[1301] Step 12:

[1302] Users read the responses displayed in the chat interface through their device. For example, by confirming a response such as, "Don't worry, B is the top-selling salesperson this month," they can quickly and appropriately obtain information.

[1303] (Example 2)

[1304] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1305] Conventional information retrieval systems have struggled to properly analyze user inquiries and efficiently retrieve relevant data. Furthermore, they have been unable to generate responses that take user emotions into account, resulting in a failure to provide users with appropriate and effective information. Especially when inquiries are complex or influenced by user emotions, more advanced analysis and responses are required.

[1306] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1307] In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for obtaining relevant data based on the analysis results via a database API, means for formatting the obtained data into a user-friendly format and generating an answer, means for sending and displaying the generated answer on a terminal, and an emotion engine that recognizes the user's emotions and reflects them in the analysis results. This makes it possible to provide appropriate information that takes into account not only the user's inquiry but also their emotions.

[1308] A "natural language processing model" is an algorithm that analyzes user inquiries and extracts important keywords and meanings.

[1309] A "database API" is an interface for accessing a database and retrieving necessary data.

[1310] An "emotion engine" is a system that recognizes emotions from the content of a user's inquiry and reflects them in the analysis results.

[1311] A "chat interface" is an interactive input method that allows users to enter inquiries using natural language.

[1312] "Analysis results" refer to the meaning and emotions behind user inquiries, as analyzed by natural language processing models and emotion engines.

[1313] "Related data" refers to information related to the user's inquiry, obtained through the database API.

[1314] A "response generation method" refers to a method of generating content to respond to the user based on the analysis results.

[1315] "Display means" refers to methods or systems for visually providing the generated response to the user.

[1316] This invention combines an emotion engine with a system that allows users to quickly access information within a company. Specific embodiments of this system will be described in detail below.

[1317] System Overview

[1318] This system consists of the following main components:

[1319] A terminal equipped with a chat interface for users to enter questions.

[1320] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[1321] Database API for retrieving related data from a database

[1322] A processing means for organizing acquired data and generating and displaying responses to the user.

[1323] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[1324] Program processing flow

[1325] The user uses their device to enter a question into the chat interface. For example, they might enter a question like, "Who is the top-selling salesperson this month?" The device receives this question and sends it to the server.

[1326] The server passes this question to a natural language processing (NLP) model and sentiment engine to analyze the query content and the user's sentiment. OpenAI's GPT-3 and BERT can be used as natural language processing models for analysis. IBM Watson and Azure Cognitive Services are available as sentiment engines.

[1327] The server uses an NLP model to analyze the intent of the question and extracts important keywords (e.g., "top sales," "this month," "sales"). Next, the server uses a database API to retrieve relevant data from a database (e.g., Salesforce).

[1328] The emotion engine analyzes user input to determine emotions and uses the analysis results (e.g., whether the user is experiencing anxiety, joy, or doubt) to format the data and generate responses.

[1329] The server organizes the data and generates responses in a format that takes the user's emotions into consideration. For example, if the user is feeling anxious, it will generate a response such as, "Don't worry, salesperson B is the top seller this month."

[1330] The server sends the generated response to the terminal. The response is displayed to the user through the chat interface. The user checks the response displayed in the chat interface through their terminal.

[1331] Specific example

[1332] A new employee enters the question, "Who is the top-selling salesperson this month?" into the chat interface. The terminal sends this question to the server. The server analyzes the question using an NLP model (e.g., GPT-3) and identifies keywords such as "top-selling," "this month," and "sales." Next, the server uses the Salesforce database API to retrieve this month's sales data. Simultaneously, it analyzes the new employee's emotions using an emotion engine (e.g., IBM Watson) and detects anxiety. Based on the retrieved data and the emotion analysis results, the server generates a basic response, "The top-selling salesperson this month is Mr. / Ms. B," and adds supplementary explanations such as "Don't worry." Finally, it sends the response to the terminal, and the new employee can check the response through the chat interface.

[1333] Examples of prompt statements include the following:

[1334] "Who is the top-selling salesperson this month?"

[1335] In this way, this system can efficiently utilize information within a company while also considering user sentiment, enabling more appropriate information acquisition. This makes it possible to achieve an even higher level of information sharing and improved operational efficiency.

[1336] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1337] Step 1:

[1338] The user enters a question into the terminal's chat interface. For example, the user might type, "Who is the top-selling salesperson this month?" The input data is the user's inquiry.

[1339] Step 2:

[1340] The terminal receives the user's question and sends it to the server. Specifically, the terminal sends the user's question data to the server using an HTTP request. The input is the question entered by the user, and the output is the question data sent to the server.

[1341] Step 3:

[1342] The server receives the question data and passes it to a natural language processing model for analysis. The server uses an NLP model (e.g., GPT-3) to analyze the intent of the question and extract important keywords (e.g., "top sales," "this month," "sales"). The input is the user's question data, and the output is a list of analyzed keywords.

[1343] Step 4:

[1344] Based on keywords extracted by the server, related data is retrieved using a database API. Specifically, the server queries data related to "the top-selling salesperson this month" via the Salesforce API. The input is a keyword list, and the output is related data retrieved from the database.

[1345] Step 5:

[1346] The server passes the question content to an emotion engine, which analyzes the user's emotions. The emotion engine (e.g., IBM Watson) is used to recognize whether the user is experiencing emotions such as anxiety, joy, or questioning. The input is the user's question data, and the output is the analyzed emotion data.

[1347] Step 6:

[1348] The server generates a response based on relevant data and sentiment analysis results. The server uses an NLG engine to generate an appropriate response based on the acquired data and sentiment analysis results. For example, it might create a response such as, "Don't worry, salesperson B is the top seller this month." The input is relevant data and sentiment data, and the output is the generated response.

[1349] Step 7:

[1350] The server sends the generated response to the terminal. The server sends the response to the terminal as an HTTP response, which the terminal receives and displays to the user. The input is the generated response data, and the output is the response sent to the terminal.

[1351] Step 8:

[1352] The user confirms the response through the chat interface on their device. For example, the user might confirm a response such as, "Don't worry, B is the top salesperson this month." The input is the response data sent from the server, and the output is the response that the user confirms.

[1353] (Application Example 2)

[1354] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1355] Current information management systems in factories often make it difficult for workers to quickly and accurately access the information they need. Furthermore, they fail to consider the emotional state of workers, leading to unclear responses or inappropriate actions. This can reduce work efficiency and increase the likelihood of errors. This invention aims to solve these problems and achieve efficient and appropriate information management.

[1356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's inquiry using a natural language processing model, means for acquiring relevant data based on the analysis results through a database API, means for formatting the acquired data into a format easily understood by the user and generating an answer, means including an emotion engine that analyzes the user's emotional state and adjusts the answer based on the analysis results, and means for transmitting and displaying the generated answer on a terminal. This makes it possible for workers to quickly and accurately access the information they need and obtain appropriate answers according to their emotional state.

[1357] A "natural language processing model" is an algorithm or machine learning model used to analyze user inquiries.

[1358] A "database API" is an application programming interface that enables access to databases and retrieval of data.

[1359] "Related data" refers to necessary information retrieved from the database based on the user's inquiry.

[1360] "Answer" refers to information provided to the user using the relevant data that has been acquired.

[1361] "Emotional state" refers to the emotional state analyzed from the user's input.

[1362] An "emotion engine" is an engine that analyzes the user's emotional state and adjusts its responses based on the analysis results.

[1363] A "chat interface" is an interface used by users to input their inquiries.

[1364] "Terminal" refers to electronic devices such as computers and mobile devices used by users.

[1365] "Analysis results" refer to the data and information obtained using natural language processing models and database APIs.

[1366] "Formatting" is the process of converting acquired data and information into a format that is easy for users to understand.

[1367] "Means" refers to methods or devices used to achieve a specific function or purpose.

[1368] This invention is a system that streamlines information management within a factory and provides appropriate responses based on the emotional state of workers. Specific embodiments are described below.

[1369] System Overview

[1370] This system consists of the following main components:

[1371] A terminal equipped with a chat interface for users to enter questions.

[1372] A server equipped with a natural language processing model to analyze user questions and identify relevant data.

[1373] Database API for retrieving related data from a database

[1374] A processing means for organizing acquired data and generating and displaying responses to the user.

[1375] An emotion engine that recognizes user emotions and takes appropriate action based on the analysis results.

[1376] Hardware and software to use

[1377] Device: A computer or mobile device operated by a user.

[1378] Server: A computer server equipped with high-performance computing resources.

[1379] Natural language processing models: For example, machine learning models such as the BERT model.

[1380] Database: Data management system within a factory (e.g., production planning database)

[1381] Emotion engine: A dedicated library or API for analyzing a user's emotional state (e.g., Sentiment Analysis API).

[1382] Program processing

[1383] The server receives the inquiry entered by the user through the terminal and analyzes the question using a natural language processing model. It extracts important keywords from the analyzed content and retrieves relevant data using a database API. Simultaneously, the emotion engine analyzes the user's emotional state, and based on that information, an optimal response is generated. This ensures that responses are tailored to the user's emotional state.

[1384] Specific examples of the system

[1385] For example, if a new worker asks, "Could you tell me this week's production plan?", the statement is transcribed into text using speech recognition. The server analyzes it using a natural language processing model and an emotion engine, and retrieves relevant production plan data from the database. The final result is displayed as, "Don't worry, this week's production plan is on track," providing the worker with appropriate information.

[1386] Example of a prompt

[1387] The prompt statement is the text input to the generative AI model, and is written as follows:

[1388] "Analyze the following text to identify key keywords (production plan, this week) and the user's sentiment: 'Please tell me this week's production plan.'"

[1389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1390] Step 1:

[1391] The user enters a question through the chat interface. The input can be in text or voice format. In the case of voice input, speech recognition software converts the speech to text. The entered question (e.g., "Please tell me this week's production plan") is sent from the terminal to the server.

[1392] Step 2:

[1393] The server passes the received question to a natural language processing (NLP) model. The NLP model analyzes the question and extracts key keywords (e.g., "this week," "production plan"). This analysis uses machine learning algorithms to understand the context of the text and grasp the user's intent. The analysis results in the extracted keywords.

[1394] Step 3:

[1395] The server calls a database API based on the analysis results to retrieve relevant data. The server generates a query containing keywords and sends it to the database. The database searches based on the query and returns the corresponding production plan data. The retrieved data (e.g., details of this week's production plan) is returned to the server.

[1396] Step 4:

[1397] The server uses an emotion engine to analyze the user's emotional state. The input question text is passed to the emotion engine, which identifies the corresponding emotion (e.g., reassurance, anxiety, excitement) from the text. The emotion engine then uses an emotion analysis algorithm to evaluate the user's emotional state. The analysis results in the user's emotional information.

[1398] Step 5:

[1399] The server integrates acquired data with sentiment analysis results to generate appropriate responses for the user. A data formatting algorithm is used to transform production plan data into a user-friendly format. The response is adjusted according to the user's emotional state to create an emotionally sensitive message (e.g., "Don't worry, this week's production plan is on track"). The generated response is stored on the server.

[1400] Step 6:

[1401] The server sends the generated response to the device. The device then displays the response again in the chat interface. This allows the user to quickly and appropriately obtain the necessary information. After the response is displayed, the user can take the next action based on the information.

[1402] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1403] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1404] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1405] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1406] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1407] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1408] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1409] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1410] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1411] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1412] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1413] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1414] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1415] 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.

[1416] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1417] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1418] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1419] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1420] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1421] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1422] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1423] The following is further disclosed regarding the embodiments described above.

[1424] (Claim 1)

[1425] A means of analyzing user inquiries using a natural language processing model,

[1426] A means of obtaining relevant data based on analysis results through a database API,

[1427] A means of formatting acquired data into a user-friendly format and generating responses,

[1428] A means of sending the generated response to the terminal and displaying it,

[1429] A system that includes this.

[1430] (Claim 2)

[1431] The system according to claim 1, further comprising means for inputting user inquiries using a chat interface.

[1432] (Claim 3)

[1433] The system according to claim 1, further comprising means for filtering the acquired relevant data based on specific criteria.

[1434]

[1435] "Example 1"

[1436] (Claim 1)

[1437] A method using a natural language processing model to analyze queries,

[1438] A means of using a database interface to acquire data based on the analysis results,

[1439] A means of formatting acquired data into a user-friendly format and generating responses,

[1440] A means of sending and displaying the generated response on the user's terminal,

[1441] A system that includes this.

[1442] (Claim 2)

[1443] The system according to claim 1, further comprising means for inputting inquiry content using a chat interface.

[1444] (Claim 3)

[1445] The system according to claim 1, further comprising means for filtering acquired data based on specific criteria.

[1446] "Application Example 1"

[1447] (Claim 1)

[1448] A means of analyzing user inquiries using a natural language processing model,

[1449] A means of obtaining relevant data based on analysis results through a database API,

[1450] A means of formatting acquired data into a user-friendly format and generating responses,

[1451] A means of sending the generated response to the terminal and displaying it,

[1452] A means to allow users to check logistics-related information in real time via an interface,

[1453] A system that includes this.

[1454] (Claim 2)

[1455] The system according to claim 1, further comprising means for inputting user inquiries using a chat interface.

[1456] (Claim 3)

[1457] The system according to claim 1, further comprising means for filtering the acquired relevant data based on specific criteria.

[1458] "Example 2 of combining an emotion engine"

[1459] (Claim 1)

[1460] A means of analyzing user inquiries using a natural language processing model,

[1461] A means of obtaining relevant data based on analysis results through a database API,

[1462] A means of formatting acquired data into a user-friendly format and generating responses,

[1463] A means of sending the generated response to the terminal and displaying it,

[1464] A means including an emotion engine that recognizes and reflects the user's emotions in the analysis results,

[1465] A system that includes this.

[1466] (Claim 2)

[1467] The system according to claim 1, further comprising means for inputting user inquiries using a chat interface.

[1468] (Claim 3)

[1469] The system according to claim 1, further comprising means for filtering the acquired relevant data based on specific criteria.

[1470] "Application example 2 when combining with an emotional engine"

[1471] (Claim 1)

[1472] A means of analyzing user inquiries using a natural language processing model,

[1473] A means of obtaining relevant data based on analysis results through a database API,

[1474] A means of formatting acquired data into a user-friendly format and generating responses,

[1475] A means including an emotion engine that analyzes the user's emotional state and adjusts the response based on the analysis results,

[1476] A means of sending the generated response to the terminal and displaying it,

[1477] A system that includes this.

[1478] (Claim 2)

[1479] The system according to claim 1, further comprising means for inputting user inquiries using a chat interface.

[1480] (Claim 3)

[1481] The system according to claim 1, further comprising means for filtering the acquired relevant data based on specific criteria. [Explanation of Symbols]

[1482] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of analyzing user inquiries using a natural language processing model, A means of obtaining relevant data based on analysis results through a database API, A means of formatting acquired data into a user-friendly format and generating responses, A means of sending the generated response to the terminal and displaying it, A system that includes this.

2. The system according to claim 1, further comprising means for inputting user inquiries using a chat interface.

3. The system according to claim 1, further comprising means for filtering acquired related data based on specific criteria.

Images