System

Abstract

To provide a system.SOLUTION: A system includes: means for searching for document data related to input information of a user using a natural language processing engine; means for analyzing an emotional context of the user using a feeling engine; means for sorting search results according to the emotional context of the user; and means for providing the user with the sorted search results.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Efficiently searching and organizing the information employees need is a key challenge in today's business environment, where there are a huge number of documents and materials. However, with conventional search systems, it is difficult for employees to accurately search and organize the information they need. [Means for solving the problem]

[0005] The present invention uses a natural language processing engine to search for documents and materials related to an employee's question or keyword, and provides the search results to the employee. Furthermore, the documents and materials are organized based on the search results. This allows employees to efficiently search for and organize the information they need. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, the natural language processing engine analyzes employee questions and keywords based on machine learning models. Specifically, when an employee enters a keyword such as "latest sales report," the natural language processing engine analyzes the keyword and searches a database for related documents and materials.

[0029] "Example 2"

[0030] The search results are provided to employees. Specifically, the search results are displayed in a list format, allowing employees to select the documents and materials they need. The search results are also displayed in order of relevance, allowing employees to quickly find the information they need.

[0031] "Example 3"

[0032] Furthermore, documents and materials are organized based on the search results. Specifically, search results are categorized and automatically stored in folders or directories corresponding to each category. For example, if there is a category called "Sales Reports," documents and materials related to this category will be automatically stored in the "Sales Reports" folder. This allows employees to efficiently search for and organize the information they need.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[0036] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[0037] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[0038] "Example 2"

[0039] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[0040] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[0041] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[0042] Step 4: The selected documents and materials will be automatically stored in folders or directories corresponding to their categories. For example, if there is a category called "Sales Reports", documents and materials related to this category will be automatically stored in the "Sales Reports" folder.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0045] For employees to perform their work efficiently, it is important to be able to quickly search and retrieve the documents and materials they need. However, with conventional systems, keyword searches were inaccurate, and it often took a long time to find relevant documents and materials. In addition, the search results were manually organized, which was inefficient and prone to errors. To solve these issues, a system with more accurate search functions and automatic organization functions was needed.

[0046] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0047] In this invention, the server includes: means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine; means for providing the search results to the employee; means for organizing the documents and materials based on the search results; means for the employee to input keywords from a terminal; means for the terminal to transmit the input keywords to the server; means for the server to pass the keywords to the natural language processing engine; means for the natural language processing engine to analyze the keywords; means for the server to search a database based on the analysis results; means for the server to return search results to the terminal; and means for the terminal to display the search results to the employee. This allows employees to quickly and accurately search for and obtain the documents and materials they need. Furthermore, the automatic organization of search results improves work efficiency and reduces errors.

[0048] A "natural language processing engine" is software that uses machine learning models to analyze human language and understand its meaning.

[0049] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[0050] A "question" is an inquiry that an employee enters to obtain information.

[0051] "Keywords" are words or phrases that employees enter to search for specific information.

[0052] "Documents" are materials such as text files and reports that contain information related to business.

[0053] "Materials" are data and documents that contain information related to business.

[0054] A "searching means" is a method for identifying relevant documents or materials using a natural language processing engine.

[0055] The "means of providing" is the method for displaying the search results to employees.

[0056] "Organization methods" are methods for categorizing documents and materials based on search results and storing them in appropriate folders or directories.

[0057] "Terminals" are devices used by employees, such as computers and smartphones.

[0058] A "server" is a computer system that receives and processes requests from terminals.

[0059] A "database" is a collection of information in which documents and materials are stored.

[0060] "Means of analysis" refers to a method of using a natural language processing engine to understand the meaning of keywords and extract related information.

[0061] "Search Results" means a list of relevant documents or materials identified by a natural language processing engine.

[0062] "Display means" refers to a method for visually displaying search results on a terminal.

[0063] This invention is a system for quickly searching and retrieving documents and materials necessary for employees to perform their work efficiently. This system has the function of analyzing employee questions and keywords using a natural language processing engine and searching a database for related documents and materials.

[0064] Hardware and software used

[0065] Hardware

[0066] Server: A powerful computer system that manages databases and runs natural language processing engines.

[0067] Devices: These are devices used by employees, such as computers and smartphones.

[0068] software

[0069] Natural language processing engine: Uses machine learning models (e.g., BERT or GPT-3®) to analyze employee questions and keywords.

[0070] Database: A collection of information in which documents and materials are stored, for example, using MySQL (registered trademark).

[0071] Data processing and calculation

[0072] The server receives keywords entered by employees on their devices and sends them to a natural language processing engine. The natural language processing engine uses a machine learning model to analyze the keywords and extract information to identify related documents and materials. The server searches a database based on the analysis results and retrieves related documents and materials. The retrieved search results are returned from the server to the device and displayed for the employee to view.

[0073] Specific examples

[0074] As a concrete example, consider the case where an employee inputs the "latest sales report." In this case, the server performs the following process.

[0075] 1. The user types "Latest sales report" into the input field on the terminal.

[0076] 2. The device sends the keyword to the server using an HTTP POST request.

[0077] 3. The server passes the keywords to a natural language processing engine.

[0078] 4. The natural language processing engine uses the BERT model to parse the "latest sales report."

[0079] 5. The server uses the analysis results to search the MySQL database and identify the latest sales report.

[0080] 6. The server returns the search results to the device in JSON format.

[0081] 7. The terminal displays the search results to the user, allowing the user to view the latest sales report.

[0082] Prompt Sentence Examples

[0083] Below is an example of a prompt that the user might enter:

[0084] "View the latest sales report."

[0085] "Please tell me your sales data for 2023."

[0086] "Look for marketing materials for new products."

[0087] In this way, the user can easily obtain the information he or she needs.

[0088] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0089] Step 1:

[0090] The user inputs a keyword from the terminal.

[0091] Specifically, the user inputs a keyword such as "latest sales report" into an input field on the terminal, and the input keyword is temporarily stored in the terminal's memory.

[0092] Input: The keyword entered by the user (e.g., "latest sales report")

[0093] Output: Keywords saved on the device

[0094] Step 2:

[0095] The terminal sends the entered keyword to the server.

[0096] Specifically, the terminal uses an HTTP POST request to send the input keyword to the server, with the keyword included in the request body.

[0097] Input: Keywords saved on your device

[0098] Output: Keywords sent to the server

[0099] Step 3:

[0100] The server passes the keywords to a natural language processing engine.

[0101] Specifically, the server passes the received keywords to the natural language processing engine, where the keywords are passed as parameters in the API request.

[0102] Input: The keyword sent to the server

[0103] Output: Keywords passed to the natural language processing engine

[0104] Step 4:

[0105] A natural language processing engine analyzes keywords.

[0106] Specifically, natural language processing engines use machine learning models (e.g., BERT or GPT-3) to analyze keywords, generating information that can be used to identify related documents and resources.

[0107] Input: Keywords passed to the natural language processing engine

[0108] Output: Analysis results (information on related documents and materials)

[0109] Step 5:

[0110] The server searches the database based on the analysis results.

[0111] Specifically, the server searches a database (e.g., MySQL) based on the analysis results. A search query is generated based on the analysis results and executed against the database.

[0112] Input: Analysis results

[0113] Output: Search results (related documents and materials) retrieved from the database

[0114] Step 6:

[0115] The server returns the search results to the device.

[0116] Specifically, the server returns the search results obtained from the database to the terminal in JSON format, etc., as an HTTP response.

[0117] Input: Search results retrieved from the database

[0118] Output: Search results sent to your device

[0119] Step 7:

[0120] The terminal displays the search results to the user.

[0121] Specifically, the terminal displays the search results received from the server on the user interface, for example, displaying a link to the latest sales report and a preview of its contents.

[0122] Input: Search results sent to your device

[0123] Output: Search results (related documents and resources) displayed to the user

[0124] (Application example 1)

[0125] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0126] Logistics centers face the challenge of making it difficult for employees to quickly obtain the information they need. In particular, there is a lack of efficient ways to search for and provide information such as inventory status, delivery schedules, and the location of items in the warehouse. This can lead to reduced operational efficiency, delays, and errors.

[0127] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0128] In this invention, the server includes means for searching for related documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing questions entered by the employee via voice or text and searching for related information from a database, and means for displaying the search results on a smartphone, thereby enabling employees to quickly obtain the information they need and improving work efficiency.

[0129] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0130] A "machine learning model" is an algorithm that learns from data and analyzes questions and keywords.

[0131] A "database" is a collection of data structured to allow efficient searching and retrieval of related information.

[0132] A "smartphone" is a portable electronic device that analyzes questions entered via voice or text and displays search results.

[0133] "Search results" are relevant information retrieved from a database based on the question or keywords analyzed by the natural language processing engine.

[0134] "Documents and materials" are any collection of text or data that contains information employees need.

[0135] "Categorization" is the process of classifying documents and materials based on search results and automatically storing them in folders or directories corresponding to their categories.

[0136] "Questions entered via voice or text" are inquiries entered by employees via their smartphones in voice or text format.

[0137] "Related information" refers to the necessary data and materials searched from the database in response to an employee's question or keyword.

[0138] A system for implementing this invention includes a natural language processing engine, a machine learning model, a database, and a smartphone. The specific configuration and operation of the system will be described below.

[0139] System configuration

[0140] 1. Natural language processing engine: Software that analyzes questions and keywords entered by employees and searches for relevant documents and materials. Specifically, it uses a natural language processing library such as spaCy.

[0141] 2. Machine learning model: An algorithm used to analyze questions and keywords. It is built using a machine learning library such as scikit-learn.

[0142] 3. Database: A structured collection of data for efficient searching and retrieval of related information. Use a database management system such as SQLite.

[0143] 4. Smartphone: A portable electronic device that allows employees to input questions by voice or text and display search results. iOS or ANDROID (registered trademark) smartphones are used.

[0144] System Operation

[0145] 1. User input: An employee uses a smartphone to input a question in voice or text format. For example, they input a prompt such as "Please tell me the latest inventory status."

[0146] 2. Natural Language Processing: The server uses a natural language processing engine to analyze the user's input and extract keywords, such as "stock status" and "latest."

[0147] 3. Database search: The server searches the database based on the extracted keywords to retrieve relevant documents and materials, for example, documents containing the latest inventory information.

[0148] 4. Providing search results: The server sends the search results to the smartphone and displays them to the user, allowing employees to quickly obtain the information they need.

[0149] Specific examples

[0150] When an employee types "Please tell me the latest inventory status" into their smartphone, the natural language processing engine extracts keywords such as "inventory status" and "latest" and searches the database for the latest inventory information. As a result, the latest inventory information is displayed on the smartphone.

[0151] Other example prompts might include questions such as "What is the latest delivery schedule?" or "Where are the items located in the warehouse?"

[0152] This system allows employees to quickly obtain the information they need, improving work efficiency.

[0153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0154] Step 1:

[0155] The user inputs a question in voice or text format using a smartphone.

[0156] Input: A user's voice or text question (e.g., "What is the latest inventory status?")

[0157] Output: Question data entered into a smartphone

[0158] How it works: A user launches an application on their smartphone and uses voice or text input. In the case of voice input, the speech recognition software converts the speech into text.

[0159] Step 2:

[0160] The server uses a natural language processing engine to analyze the user's input and extract keywords.

[0161] Input: User's question data (text format)

[0162] Output: Extracted keywords (e.g., "Availability", "Latest")

[0163] How it works: The server uses a natural language processing library such as spaCy to analyze the text and extract important keywords, for example, by performing morphological analysis to identify important words such as nouns and verbs.

[0164] Step 3:

[0165] The server searches the database based on the extracted keywords to retrieve related documents and materials.

[0166] Input: Extracted keywords (e.g., "inventory status," "latest")

[0167] Output: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[0168] Specific operation: The server uses a database management system such as SQLite to search for documents or materials that match the keywords, for example, by executing an SQL query to retrieve records that match the keywords.

[0169] Step 4:

[0170] The server sends the search results to the smartphone and displays them to the user.

[0171] Input: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[0172] Output: Search results displayed on a smartphone

[0173] Specific operation: The server converts the search results into a data format such as JSON and sends it to the smartphone. The smartphone application analyzes the received data and displays it in a format that is easy for the user to view.

[0174] Step 5:

[0175] The user checks the search results displayed on the smartphone and obtains the information they need.

[0176] Input: Search results displayed on smartphone

[0177] Output: The information the user needs (e.g., the latest inventory information)

[0178] Specific operation: The user checks the search results displayed on the smartphone screen and obtains the necessary information, such as stock availability and delivery schedules.

[0179] Example 2

[0180] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] Employees need to be able to search for the documents and materials they need quickly and efficiently, and to receive results organized in order of relevance. However, with conventional systems, search results were not properly organized, making it time-consuming to find the information they needed. Furthermore, the display format of search results was inappropriate, making it difficult for users to quickly find the information they needed.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0183] In this invention, the server includes means for searching for documents and materials related to employee questions and keywords using a natural language processing engine, means for sorting the search results in descending order of relevance, and means for generating a list of the search results, thereby enabling employees to quickly and efficiently find the information they need.

[0184] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0185] "Searching tools" is the ability to find documents and materials in the database based on employee questions or keywords.

[0186] The "means of providing" is the function for displaying search results to employees.

[0187] "Sorting means" is a function for organizing search results in order of relevance.

[0188] The "means for generating" is a function for formatting search results in a list format.

[0189] The "display means" is a function for displaying the generated search results on the employee's terminal.

[0190] A "machine learning model" is an algorithm that analyzes questions and keywords based on data.

[0191] "Categorization means" is a function that categorizes search results based on specific criteria and automatically stores them in folders or directories corresponding to each category.

[0192] MODE FOR CARRYING OUT THE INVENTION

[0193] The present invention is a system that enables employees to quickly and efficiently search for documents and materials they need, and provides results organized in order of relevance. Specific embodiments of this system are described below.

[0194] System configuration

[0195] The system consists of three main components: a server, a terminal, and a user. The server uses a natural language processing engine and machine learning models to analyze search queries and retrieve relevant documents and materials. The terminal is a device where users input search queries and display search results. The user is an employee who uses the system to search for the information they need.

[0196] Hardware and software used

[0197] Server: Use a computer system equipped with a high-performance processor and large memory capacity. A Python (registered trademark)-based library (e.g., NLTK, spaCy) will be installed on the server as a natural language processing engine. ElasticSearch (registered trademark) will be used as the search algorithm.

[0198] Terminal: A device used by a user, such as a PC or smartphone, on which a web browser and dedicated applications are installed.

[0199] Software: We use machine learning models (e.g., BERT, GPT) to analyze search queries, which allows us to analyze user questions and keywords with high accuracy.

[0200] System Operation

[0201] 1. User enters a search query

[0202] The user enters the required information into the device's search bar, for example, "project report."

[0203] 2. The device sends the search query to the server

[0204] The device sends the search query entered by the user to the server using an HTTP request.

[0205] 3. The server receives the search query and queries Elasticsearch

[0206] The server analyzes the search query received from the terminal and sends a search request to Elasticsearch.

[0207] 4. The server receives the search results from Elasticsearch

[0208] The server receives search results returned from Elasticsearch, which contain relevant document and resource information.

[0209] 5. The server sorts the search results by relevance.

[0210] The server sorts the received search results in order of relevance, using Elasticsearch's scoring function to evaluate relevance.

[0211] 6. The server generates a list of search results

[0212] The server formats the sorted search results into a list in HTML format.

[0213] 7. The server sends the search results to the device.

[0214] The server sends the generated search results in HTML format to the terminal using an HTTP response.

[0215] 8. The device displays the search results to the user.

[0216] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format.

[0217] 9. The user selects the documents and materials they need.

[0218] Users can select the documents or materials they need from the displayed search results, and click on the selected document to display details.

[0219] Specific examples

[0220] As a concrete example, consider the case where a user searches for "project report." The user enters "project report" into the terminal and clicks the search button. The server receives this query and uses Elasticsearch to search for documents in the database. The search results are sorted in order of relevance and displayed to the user in a list format. The user can then select the document they need from this list.

[0221] Prompt Sentence Examples

[0222] An example of a prompt sentence might be:

[0223] Prompt: "Find project reports"

[0224] When this prompt is input into the generative AI model, the AI ​​model will provide search results to help employees quickly find the project report they need.

[0225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0226] Step 1:

[0227] The user enters a search query.

[0228] The user enters the required information into the device's search bar, for example, "project report," and the query is temporarily stored in the device's memory.

[0229] Step 2:

[0230] The device sends a search query to the server.

[0231] The device sends the search query entered by the user to the server as an HTTP request. This request includes the query entered by the user. After sending the request, the device waits for a response from the server.

[0232] Step 3:

[0233] The server receives the search query and queries Elasticsearch.

[0234] The server analyzes the search query received from the device and sends a search request to Elasticsearch. Specifically, the server passes the search query to Elasticsearch's API, instructing it to search for related documents and materials. The input is the search query, and the output is the search results from Elasticsearch.

[0235] Step 4:

[0236] The server receives the search results from Elasticsearch.

[0237] The server receives the search results returned from Elasticsearch. The search results contain information about related documents and resources. The server stores the results in memory for further processing. The input is the search results from Elasticsearch, and the output is the search results stored in the server's memory.

[0238] Step 5:

[0239] The server sorts the search results by relevance.

[0240] The server uses Elasticsearch's scoring function to sort the received search results in order of relevance. Specifically, it calculates the relevance score of each document and sorts them in order of highest to lowest. The input is the search results stored in the server's memory, and the output is the sorted search results.

[0241] Step 6:

[0242] The server generates the search results in a list format.

[0243] The server formats the sorted search results into a list in HTML format. Specifically, it wraps the title and summary of each document in HTML tags to make it easier for users to view. The input is the sorted search results, and the output is the HTML-formatted search results.

[0244] Step 7:

[0245] The search results generated by the server are sent to the terminal.

[0246] The server generates the search results in HTML format and sends them to the terminal as an HTTP response. The input is the search results in HTML format, and the output is the search results sent to the terminal.

[0247] Step 8:

[0248] The terminal displays the search results to the user.

[0249] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format. Specifically, the web browser parses the HTML and displays it on the screen. The input is the HTML search results received from the server, and the output is the search results displayed to the user.

[0250] Step 9:

[0251] The user selects the documents and materials they need.

[0252] The user selects the necessary documents or materials from the displayed search results. Clicking on the selected document displays details. The input is the user's click operation, and the output is a detailed display of the selected document.

[0253] (Application example 2)

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

[0255] At logistics centers, employees are required to quickly search for necessary inventory and delivery information and carry out their work efficiently. However, with conventional systems, searching for information takes time and displays a lot of irrelevant information, resulting in reduced work efficiency. Furthermore, information search using smartphones is not fully utilized, making it difficult to respond quickly on-site.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0257] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for displaying inventory information and delivery information in order of relevance, and means for employees to quickly search for necessary information using their smartphones, thereby enabling employees to quickly search for necessary information and improving work efficiency.

[0258] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0259] "Means for providing search results" refers to a function for displaying searched documents and materials to employees.

[0260] "Means for organizing documents and materials" refers to a function that categorizes documents and materials based on search results and automatically stores them in folders or directories corresponding to each category.

[0261] "A means for displaying inventory information and delivery information in order of relevance" is a function for sorting and displaying inventory data and delivery data in order of relevance based on a search query.

[0262] "Means for employees to quickly search for the information they need using their smartphones" refers to a function that allows employees to quickly search for the information they need using their smartphones.

[0263] A system for carrying out the present invention enables employees at a logistics center to quickly search for necessary inventory information and delivery information. A specific embodiment of this system will be described below.

[0264] System configuration

[0265] The system consists of the following main components:

[0266] 1. Server: Equipped with a natural language processing engine and machine learning models, it analyzes employee questions and keywords.

[0267] 2. Smartphone: Enter a search query on the employee's device and view the search results.

[0268] 3. Database: Stores inventory and shipping information.

[0269] Program processing

[0270] The server works as follows:

[0271] 1. Natural language processing engine: Analyzes questions and keywords entered by employees on their smartphones and searches for relevant documents and materials.

[0272] 2. Machine learning models: Generate search results in order of relevance based on an analysis of the question and keywords.

[0273] 3. Providing search results: Search results are sent to employees' smartphones and provided to them.

[0274] 4. Data organization: Documents and materials are categorized based on search results and automatically stored in folders and directories corresponding to each category.

[0275] 5. Display inventory and shipping information: Display inventory and shipping data sorted by relevance.

[0276] Hardware and software used

[0277] Hardware: Smartphones, servers

[0278] Software: Python, Pandas, Scikit-learn, natural language processing engine (e.g., SpaCy)

[0279] Specific examples

[0280] When an employee searches for "out of stock items," the system works as follows:

[0281] 1. An employee types "out of stock item" into their smartphone.

[0282] 2. The server's natural language processing engine parses the query and searches for relevant inventory information.

[0283] 3. The machine learning model generates search results in order of relevance.

[0284] 4. Search results are displayed on a smartphone, allowing employees to see a list of items that are out of stock.

[0285] Prompt Sentence Examples

[0286] Search query: "out of stock items"

[0287] In this way, logistics center employees can quickly find the information they need and improve work efficiency.

[0288] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0289] Step 1:

[0290] A user types a search query into their smartphone.

[0291] Input: A user types "item out of stock" into their smartphone.

[0292] Output: The search query is sent to the server.

[0293] Specific operation: The user enters "out of stock items" into the search bar on their smartphone and presses the search button.

[0294] Step 2:

[0295] The server analyzes the search query using a natural language processing engine.

[0296] Input: A search query sent from a smartphone: "Products out of stock."

[0297] Output: Parsed query data.

[0298] What it does: The server's natural language processing engine (e.g., SpaCy) tokenizes the search query and extracts key keywords.

[0299] Step 3:

[0300] The server uses machine learning models to search for relevant documents and materials.

[0301] Input: Parsed query data.

[0302] Output: A list of relevant documents and materials.

[0303] What it does: The server's machine learning model (e.g., Scikit-learn) uses the parsed query data to search for inventory and delivery information in the database and sort it by relevance.

[0304] Step 4:

[0305] The server sends the search results to the smartphone.

[0306] Input: List of relevant documents and materials.

[0307] Output: Search results displayed on a smartphone.

[0308] Specific operation: The server sends a list of relevant documents and materials to the smartphone and displays it to the user.

[0309] Step 5:

[0310] The user checks the search results on their smartphone.

[0311] Input: Search results displayed on a smartphone.

[0312] Output: The user confirms the required information.

[0313] Specific behavior: The user scrolls through the search results displayed on their smartphone screen and checks the necessary inventory and delivery information.

[0314] Step 6:

[0315] The server organizes documents and materials based on the search results.

[0316] Input: List of relevant documents and materials.

[0317] Output: Categorized documents and materials.

[0318] Specific operation: The server categorizes documents and materials based on the search results and automatically stores them in folders or directories corresponding to each category.

[0319] Step 7:

[0320] The server displays inventory and delivery information in order of relevance.

[0321] Input: Relevant inventory and shipping information.

[0322] Output: Stock and shipping information sorted by relevance.

[0323] Specific behavior: The server sorts inventory and shipping data in order of relevance and displays it to the user.

[0324] Example 3

[0325] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0326] There is a problem that it is difficult for employees to efficiently search and organize the information they need. Especially when there are a large number of documents and materials, manual searching and organization takes time and effort, reducing work efficiency. In addition, if search results are not properly categorized, it is difficult to quickly find the information you need.

[0327] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for searching for relevant information based on the employee's question or keyword using a natural language processing engine, means for providing the employee with the search results, means for analyzing and categorizing information based on the search results, and means for automatically storing the categorized information in folders or directories corresponding to each category. This enables employees to efficiently search for and organize the information they need.

[0328] A "natural language processing engine" is software that analyzes natural language and understands its meaning.

[0329] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[0330] "Questions and keywords" are input data that employees use to search for information.

[0331] "Relevant information" refers to documents and materials retrieved based on an employee's question or keywords.

[0332] "Search methods" are methods and techniques for obtaining relevant information based on employee questions or keywords.

[0333] "Means of providing" refers to the methods and technologies used to display search results to employees.

[0334] "Means for analyzing and categorizing" refers to the methods and techniques used to analyze and categorize search results into specific categories.

[0335] "Folders and directories" are virtual storage locations for organizing information within a computer.

[0336] "Automatic storage means" refers to methods or techniques for automatically moving analyzed information into corresponding folders or directories.

[0337] A "machine learning model" is an algorithm that learns from data and makes predictions and classifications.

[0338] The present invention is a system for enabling employees to efficiently search for and organize necessary information. A specific embodiment of this system will be described below.

[0339] System configuration

[0340] This system consists of three main components: a server, a terminal, and a user.

[0341] 1. Server:

[0342] The server uses a natural language processing engine to search for relevant information based on employee questions and keywords. Specifically, it uses search engines such as Apache (registered trademark) Solr and Elasticsearch. It also uses natural language processing tools such as Google (registered trademark) Cloud Natural Language API and IBM Watson (registered trademark) Natural Language Understanding to analyze and categorize the search results. It then uses the Python os and shutil modules to automatically store the categorized information in the corresponding folders and directories.

[0343] 2. Terminal:

[0344] A terminal is a device on which a user inputs a search query and checks search results. Terminals include computing devices such as PCs, tablets, and smartphones.

[0345] 3. User:

[0346] Users are employees who use the system to search and organize information. Users use terminals to enter search queries and view organized information.

[0347] System Operation

[0348] 1. User enters a search query:

[0349] Users enter a question or keyword into the device's search bar, for example, "Sales report 2023."

[0350] 2. Server retrieves search results:

[0351] The server receives the search query entered by the user and retrieves relevant information from the database using Apache Solr or Elasticsearch.

[0352] 3. Server analysis and categorization of search results:

[0353] The server analyzes the search results using Google Cloud Natural Language API or IBM Watson Natural Language Understanding and categorizes them into appropriate categories, such as "sales reports," "financial reports," and "market analysis."

[0354] 4. Server stores files in folders by category:

[0355] The server automatically stores the categorized information in folders or directories corresponding to each category using the Python os and shutil modules. For example, information categorized as "Sales Report" is stored in the "Sales Report" folder.

[0356] 5. User review of organized information:

[0357] The user can use the device to view the organized folders, for example, by opening the "Sales Report" folder and viewing the information they need.

[0358] Examples of specific examples and prompts

[0359] Examples:

[0360] When a user searches for "Sales Report 2023", the specific operations are as follows:

[0361] 1. User: Enter "Sales Report 2023" into the device's search bar and click the search button.

[0362] 2. Server: Receives search queries and retrieves relevant information from the database using Apache Solr.

[0363] 3. Server: Analyze the acquired information using the Google Cloud Natural Language API and classify it into the "Sales Report" category.

[0364] 4. Server: Use Python's os module to move the classified information to the "Sales Report" folder.

[0365] 5. User: Open the "Sales Report" folder on the device and check the required information.

[0366] Example prompt sentence:

[0367] "Search for sales reports for 2023 and automatically store the relevant information in the sales reports folder."

[0368] This system allows users to efficiently search and organize the information they need. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0369] Step 1: User enters a search query

[0370] A user enters a question or keyword into the device's search bar. For example, they might enter "Sales Report 2023." The input data is text about the information the user wants to search for. The output is sent to the server as a search query.

[0371] Step 2: Server retrieves search results

[0372] The server receives a search query entered by a user and retrieves relevant information from a database using a search engine (e.g., Apache Solr or Elasticsearch). The input data is the user's search query. The server sends the search query to the search engine to retrieve relevant documents and materials. The output is a list of documents and materials as search results.

[0373] Step 3: Server analyzes and categorizes search results

[0374] The server analyzes the search results using a natural language processing engine (for example, Google Cloud Natural Language API or IBM Watson Natural Language Understanding). The input data are the documents and materials obtained as search results. The server analyzes these documents and classifies them into appropriate categories. For example, they could be categorized as "sales reports," "financial reports," or "market analysis." The output is a list of categorized documents and materials.

[0375] Step 4: The server stores the categories in folders

[0376] The server automatically stores categorized documents and materials in folders and directories corresponding to each category. The input data are categorized documents and materials. The server uses Python's os module and shutil module to obtain the document path and move it to the corresponding folder. For example, documents categorized in the "Sales Report" category are stored in the "Sales Report" folder. The output is the documents and materials stored in the folder.

[0377] Step 5: User reviews the organized information

[0378] The user uses a terminal to check the organized folders. The input data are the documents and materials stored in the folders. The user can open, for example, the "Sales Report" folder and view the necessary documents. The output is the documents and materials that the user views.

[0379] This system allows users to efficiently search and organize the information they need.

[0380] (Application example 3)

[0381] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0382] In conventional document management systems, searching and organizing documents and materials is often done manually, resulting in inefficiencies. Furthermore, many paper-based documents are used at logistics centers and other on-site locations, creating a need for a way to digitize and efficiently manage them. Furthermore, categorizing documents and uploading them to cloud storage is often done manually, which is time-consuming and labor-intensive.

[0383] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0384] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for extracting text from images using optical character recognition technology, means for categorizing the documents based on the extracted text and automatically storing them in corresponding folders, and means for uploading the documents to cloud storage, thereby enabling efficient search, organization, digitization, and automatic uploading of documents and materials to cloud storage.

[0385] A "natural language processing engine" is software that analyzes natural language and searches for relevant information based on questions or keywords.

[0386] "Employee" refers to a person who belongs to a company or organization and performs work.

[0387] "Search methods" refer to methods and techniques for finding specific information.

[0388] "Means of delivery" refers to the methods and technologies used to display or make accessible search results to users.

[0389] "Organizational methods" refer to methods and techniques for classifying and managing documents and materials based on specific criteria.

[0390] "Optical character recognition technology" is a technology for extracting character information from images.

[0391] "Image" refers to a digital file containing visual information.

[0392] "Text" refers to digital data containing textual information.

[0393] "Categorization" refers to classifying information based on specific criteria.

[0394] A "folder" refers to a virtual container for organizing digital data.

[0395] "Cloud storage" refers to a remote server for storing data over the Internet.

[0396] "Upload" refers to the transfer of data from a local device to a remote server.

[0397] A system for implementing this invention is configured as follows: First, the server uses a natural language processing engine to search for relevant documents and materials based on the employee's question and keywords. The natural language processing engine analyzes the question and keywords based on a machine learning model. The analyzed results are provided to the employee.

[0398] The server then organizes the documents and materials based on the search results. To organize them, it uses optical character recognition (OCR) technology to extract text from images. The extracted text is then categorized based on specific keywords and automatically stored in corresponding folders. The documents are then uploaded to cloud storage.

[0399] To realize this system, the following hardware and software are used: A smartphone with a camera is required for the hardware, and Python, an OCR library, PIL (Python Imaging Library), and Google Cloud Storage are used for the software.

[0400] As a concrete example, consider a document organization app used in a logistics center. When an employee takes a photo of a shipping instruction sheet with their smartphone camera, the image is converted into text using OCR technology. The converted text is classified into a category called "Shipping Instructions" and automatically stored in the corresponding folder. The document is then uploaded to cloud storage.

[0401] An example of a prompt sentence might be:

[0402] "Please develop a document organization app to be used in a logistics center. This application will analyze document images taken with a smartphone camera using OCR technology, automatically classify them into categories such as shipping instructions, receipts, and inventory lists, and upload them to cloud storage."

[0403] In this way, documents and materials can be efficiently searched, organized, digitized and automatically uploaded to cloud storage.

[0404] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0405] Step 1:

[0406] The user takes a photo of the document using the smartphone camera.

[0407] Input: Paper-based document

[0408] Output: Digital image file

[0409] Specific operation: The user launches the smartphone's camera app and takes a photo of a document. The captured image is saved in the smartphone.

[0410] Step 2:

[0411] The device uses optical character recognition (OCR) technology to extract text from the image.

[0412] Input: Digital image file

[0413] Output: Extracted text data

[0414] Specific operation: The device inputs the saved image file into OCR software and extracts the text information in the image as text data.

[0415] Step 3:

[0416] The device analyzes the extracted text and categorizes it.

[0417] Input: Extracted text data

[0418] Output: Category information

[0419] Specific operation: The terminal analyzes the extracted text data and determines categories based on specific keywords (e.g., "shipping instructions," "receipt," etc.).

[0420] Step 4:

[0421] The terminal automatically stores the documents in the corresponding folders based on the categories.

[0422] Input: Category information, digital image files

[0423] Output: Documents stored in a folder

[0424] Specific operation: The terminal moves or copies the digital image files to the corresponding folders based on the determined categories.

[0425] Step 5:

[0426] The device uploads the document to cloud storage.

[0427] Input: Documents stored in a folder

[0428] Output: Documents saved in cloud storage

[0429] Specific operation: The device uploads the documents in the folder to a cloud storage service (Google Cloud Storage). Once the upload is complete, the documents are stored in the cloud.

[0430] Step 6:

[0431] The server uses a natural language processing engine to search for relevant documents and materials based on the employee's questions and keywords.

[0432] Input: Employee question or keyword

[0433] Output: Search results for related documents and resources

[0434] Specific operation: The server inputs the questions and keywords entered by the employee into a natural language processing engine to search for relevant documents and materials, and provides the search results to the employee.

[0435] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0436] "Example 1"

[0437] In one embodiment of the present invention, a natural language processing engine is combined with an emotion engine. When an employee enters a question or keywords into the system, the natural language processing engine analyzes the keywords and searches a database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question and keywords. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine recognizes the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[0438] "Example 2"

[0439] In another embodiment of the present invention, an emotion engine organizes documents and materials based on the employee's emotional context. Specifically, the emotion engine analyzes the employee's emotional context and automatically stores documents and materials in folders or directories corresponding to the respective emotional context. For example, if an employee types the phrase "I can't find the sales report," the emotion engine recognizes the employee's frustration from this phrase, and the system automatically stores the relevant documents and materials in a "Frustration" folder.

[0440] "Example 3"

[0441] In one embodiment of the present invention, a natural language processing engine is combined with an emotion engine. When an employee enters a question or keywords into the system, the natural language processing engine analyzes the keywords and searches a database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question and keywords. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine recognizes the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[0442] The processing flow of each embodiment will be described below.

[0443] "Example 1"

[0444] Step 1: An employee enters a question or keyword into the system.

[0445] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and materials.

[0446] Step 3: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[0447] Step 4: The natural language processing engine uses the results of the emotion engine's analysis to provide more relevant documents and materials.

[0448] "Example 2"

[0449] Step 1: An employee enters a question or keyword into the system.

[0450] Step 2: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[0451] Step 3: Based on the analysis results of the emotion engine, documents and materials are automatically stored in folders and directories that correspond to their emotional context.

[0452] Example 1

[0453] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0454] Conventional systems were unable to consider emotional context when searching for documents and materials related to questions or keywords entered by employees, making it difficult to fully meet employees' needs. Furthermore, the organization and provision of search results did not provide appropriate information that reflected employees' emotions, hindering efficient work execution.

[0455] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0456] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the emotional context of the employee questions and keywords using an emotion engine, and means for providing highly relevant documents and materials based on the emotional context. This makes it possible to provide appropriate information that takes employee emotions into consideration, thereby improving work efficiency and employee satisfaction.

[0457] A "natural language processing engine" is software that analyzes questions and keywords entered by employees, understands their meaning, and searches for related documents and materials.

[0458] A "machine learning model" is an algorithm that learns from data and finds patterns and rules, and is used to improve the analytical capabilities of natural language processing engines.

[0459] The "emotion engine" is software that analyzes the emotional context contained in employees' questions and keywords and recognizes those emotions.

[0460] "Documents and materials" is a general term for texts, reports, presentations, data sheets, etc. that contain information employees need to perform their jobs.

[0461] A "database" is an information system for efficiently storing, searching, and managing documents and materials.

[0462] "Search Results" are a list of documents or materials retrieved from a database based on a question or keywords analyzed by a natural language processing engine and sentiment engine.

[0463] "Categorization" is the process of classifying documents or materials based on search results according to specific themes or attributes.

[0464] A "folder or directory" is a virtual storage location on a computer for organizing and storing documents and materials.

[0465] An "employee" is a user who uses the system to input questions or keywords to carry out work.

[0466] MODE FOR CARRYING OUT THE INVENTION

[0467] This invention is a system that analyzes questions and keywords entered by employees and provides relevant documents and materials. The system combines a natural language processing engine and an emotion engine to provide information that takes into account the employee's emotional context.

[0468] Hardware and software used

[0469] server

[0470] The server performs the main processing of the system using the following software:

[0471] Natural language processing engines (e.g., BERT, GPT-3)

[0472] Emotion engine (e.g., emotion analysis API)

[0473] Database management systems (e.g., MySQL, PostgreSQL)

[0474] Terminal

[0475] The terminal provides an interface for employees to enter questions or keywords. The terminal uses the following software:

[0476] Web browser or dedicated application

[0477] HTTP client library

[0478] User

[0479] The user (employee) enters a question or keyword into the system and checks the search results.

[0480] Data processing and calculation

[0481] Natural Language Processing Engine

[0482] The server passes the questions and keywords entered by employees to a natural language processing engine for analysis. The natural language processing engine uses machine learning models (e.g., BERT, GPT-3) to understand the meaning of the input text and extract keywords to search for related documents and materials.

[0483] Emotion Engine

[0484] The server passes the input text to an emotion engine that analyzes the emotional context. The emotion engine recognizes the employee's emotions (e.g., frustration, joy) from the input text and uses that information to provide relevant documents and resources.

[0485] Database search

[0486] The server uses the results of the natural language processing and emotion engines to search for relevant documents and materials from the database, and the search results are prioritized taking into account the employee's emotional context.

[0487] Providing and organizing results

[0488] The server sends the search results to the terminal, which displays them to the user. Furthermore, the terminal categorizes the documents and materials based on the search results and automatically stores them in folders and directories corresponding to each category.

[0489] Specific examples

[0490] If an employee types "I can't find the latest sales report," the device sends this input to the server. The server uses a natural language processing engine to analyze the keyword "latest sales report" and an emotion engine to recognize the employee's frustration from the phrase "I can't find it." The server uses this information to search for relevant documents in the database and sends the search results to the device. The device then displays the search results to the user.

[0491] Prompt Sentence Examples

[0492] "If an employee types into the system, 'I can't find the latest sales report,' how would the system respond?"

[0493] By feeding this prompt into a generative AI model, a response is obtained that details the system's behavior.

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1:

[0496] The user enters a question or keyword.

[0497] The user enters a question or keyword, such as "I can't find the latest sales report," into the system interface. The entered text is displayed in the input field on the device. Specific actions include the user entering text using the keyboard and clicking the send button.

[0498] Step 2:

[0499] The device sends input to the server.

[0500] The terminal sends the text entered by the user to the server. The input text is sent to the server as an HTTP request. Specifically, the terminal application generates an HTTP request and sends it to the server.

[0501] Step 3:

[0502] The server analyzes the input using a natural language processing engine.

[0503] The server passes the received text to a natural language processing engine for analysis. By analyzing the input text, related keywords and phrases are extracted. Specifically, the server calls the API of the natural language processing engine to obtain the analysis results. The input is the user's text, and the output is the analyzed keywords and phrases.

[0504] Step 4:

[0505] The server analyzes the emotional context with an emotion engine.

[0506] The server passes the input text to the emotion engine and analyzes the emotional context. The emotion engine recognizes the employee's emotion (e.g., frustration) from the input text. Specifically, the server calls the emotion engine's API to obtain the emotion analysis results. The input is the user's text, and the output is the analyzed emotional information.

[0507] Step 5:

[0508] The server searches the database for relevant documents and materials.

[0509] The server searches the database for relevant documents and materials based on the analysis results of the natural language processing engine and emotion engine. The search results are prioritized taking into account the employee's emotional context. Specifically, the server generates an SQL query and executes the search against the database. The input is the analysis result, and the output is a list of the retrieved documents and materials.

[0510] Step 6:

[0511] The server sends the search results to the terminal.

[0512] The server sends the search results to the terminal. The search results are sent to the terminal as an HTTP response. In concrete terms, the server generates an HTTP response and sends it to the terminal. The input is the search results, and the output is the data sent to the terminal.

[0513] Step 7:

[0514] The terminal displays the search results to the user.

[0515] The terminal displays the search results received from the server to the user, who can then check related documents and materials. Specifically, the terminal application displays the search results on the screen. The input is data from the server, and the output is the search results displayed to the user.

[0516] (Application example 1)

[0517] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0518] It is important for employees to be able to quickly and accurately search for and obtain the documents and materials they need within the factory. However, with conventional systems, it often took employees a long time to find the information they needed, reducing efficiency. Furthermore, providing information without taking into account the emotional state of employees can increase stress and frustration. To solve these problems, support that takes into account the emotional context is needed, rather than simply analyzing employees' questions and keywords and providing relevant documents and materials.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0520] In this invention, the server includes means for searching for relevant documents and materials based on the employee's questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the emotional context of the employee's questions and keywords using a sentiment analysis engine, and means for providing additional support to the employee based on the emotional context, thereby enabling the employee to not only quickly and accurately obtain the information they need, but also receive emotional support.

[0521] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0522] A "machine learning model" is an algorithm that learns from data and analyzes employee questions and keywords.

[0523] A "sentiment analysis engine" is software that analyzes the emotional context of employee questions and keywords.

[0524] "Documents and materials" includes information such as manuals, work instructions, and reports used within the factory.

[0525] "Search Results" means a list of relevant documents or materials retrieved by a natural language processing engine.

[0526] "Categorization" is the process of classifying documents or materials into specific categories based on search results.

[0527] A "folder or directory" is a digital storage location for organizing and storing documents and materials.

[0528] "Additional support" is encouragement or additional information provided based on the emotional context analyzed by the sentiment analysis engine.

[0529] To implement this invention, the following hardware and software are used. The hardware includes a robot body used in a factory, a built-in microphone and speaker, and a display. The software includes a natural language processing engine (e.g., spaCy, BERT), a sentiment analysis engine (e.g., IBM Watson Tone Analyzer), a database management system (e.g., MySQL, PostgreSQL), and robot control software (e.g., ROS - Robot Operating System).

[0530] When an employee speaks a question or keyword to the robot, the server uses a built-in microphone to capture the voice and converts it into text using speech recognition software (e.g., Google Speech-to-Text API). A natural language processing engine then analyzes the converted text and extracts the keywords and intent of the question. For example, if an employee says, "Show me the latest work order," the server extracts the keyword "latest work order."

[0531] The sentiment analysis engine then analyzes the emotional context of the text. For example, if "I can't find the work instructions," it will detect frustration. The server then searches the database for relevant documents and materials based on the extracted keywords. For example, it retrieves documents related to "latest work instructions" from the database.

[0532] The search results are displayed on the screen and the employee is notified by voice. Based on the results of sentiment analysis, words of encouragement or additional support can be provided as needed. For example, a response could be, "I see you're having trouble finding the work instruction. We'll search for it right away, so please wait a moment."

[0533] As a concrete example, the following prompt sentence is shown.

[0534] Employee: "Show me the latest work order."

[0535] Robot: "Retrieving the latest work orders. Please wait."

[0536] (After database search)

[0537] Robot: "Here's the latest work order. I've put it on the screen."

[0538] As a concrete example of emotion analysis, the following exchange can be considered:

[0539] Employee: "I can't find the work order, what do I do?"

[0540] Robot: "I see you're having trouble finding your work order. I'll search for it right away, so please wait a moment."

[0541] (After database search)

[0542] Robot: "Here's your latest work order. I've put it up on the screen. Is there anything else I can help you with?"

[0543] In this way, employees not only get the information they need quickly and accurately, but also receive emotional support.

[0544] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0545] Step 1:

[0546] The user inputs questions or keywords to the robot by voice.

[0547] Input: User voice input

[0548] Output: Audio data

[0549] Specific behavior: The user says to the robot, "Show me the latest work instructions."

[0550] Step 2:

[0551] The robot's built-in microphone captures the voice and converts it into text using speech recognition software (e.g., Google Speech-to-Text API).

[0552] Input: Audio data

[0553] Output: Text data

[0554] Specific operation: The robot records the user's voice and converts the voice data into text.

[0555] Step 3:

[0556] The server uses a natural language processing engine (e.g., spaCy, BERT) to analyze the converted text and extract keywords and the intent of the question.

[0557] Input: Text data

[0558] Output: Extracted keywords and intent

[0559] Specific operation: The server extracts the keyword "latest work instructions" from the text "Show me the latest work instructions."

[0560] Step 4:

[0561] The server uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the emotional context of the text.

[0562] Input: Text data

[0563] Output: Emotion analysis results

[0564] What happens: The server detects frustration from the text "Work order not found."

[0565] Step 5:

[0566] The server searches the database for relevant documents and materials based on the extracted keywords.

[0567] Input: Extracted keywords

[0568] Output: Search results (related documents and materials)

[0569] Specific operation: The server searches the database using the keyword "latest work instructions" and retrieves relevant documents.

[0570] Step 6:

[0571] The server displays the search results on the display and notifies the user by voice.

[0572] Input: Search results

[0573] Output: Display and audio notification

[0574] Specific operation: The server will announce "This is the latest work instruction. It is displayed on the screen" and display the document on the screen.

[0575] Step 7:

[0576] The server then provides words of encouragement or additional support as needed based on the results of the sentiment analysis.

[0577] Input: Sentiment analysis results

[0578] Output: Additional support (e.g., words of encouragement)

[0579] Specific operation: The server will notify you by voice, "I see you're having trouble finding the work instructions. We'll search for them right away, so please wait a moment."

[0580] Example 2

[0581] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0582] It is difficult for employees to quickly and efficiently find the documents and materials they need. Information is provided without considering employees' emotional context, which can increase employee stress and frustration. Furthermore, there is a lack of ways to organize documents and materials based on employees' emotions, making information management cumbersome.

[0583] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0584] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion analysis engine, and means for automatically storing the documents and materials in specific folders or directories based on the emotional context. This enables employees to find the information they need quickly and efficiently, and organizing information based on emotional context can reduce employee stress and frustration.

[0585] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0586] A "machine learning model" is an algorithm that learns patterns based on data and makes predictions and classifications.

[0587] An "emotion analysis engine" is software that analyzes the emotional context of text entered by employees.

[0588] A "folder or directory" is a digital repository for organizing and storing documents and materials.

[0589] "Search results" are the list of relevant documents and resources returned by the search engine based on the employee's question or keywords.

[0590] "Employee" means a user who uses the system to search and organize documents and materials.

[0591] "Documents and materials" are digital files containing information that employees need to perform their jobs.

[0592] "Emotional context" refers to the feelings and mental state that can be read from the text entered by an employee.

[0593] This invention is a system that enables employees to quickly and efficiently find documents and materials they need. The system is composed of a server that includes a natural language processing engine, a sentiment analysis engine, a search engine, and a database, and a terminal operated by a user.

[0594] The server receives search queries entered by employees on their devices and analyzes them using a natural language processing engine. The natural language processing engine incorporates machine learning models to understand the employee's questions and keywords and search for relevant documents and materials. The search engine uses common search software such as Apache Solr and Elasticsearch.

[0595] The search results are displayed in a list format in order of relevance. The server provides the search results to the user's terminal, and the user can select the documents or materials they need.

[0596] The server then uses a sentiment analysis engine to analyze the employee's emotional context. The sentiment analysis engine uses sentiment analysis APIs from IBM Watson and Microsoft® Azure®. It recognizes emotions from phrases and search queries entered by employees and organizes documents and materials accordingly. For example, if an employee enters the phrase "I can't find the sales report," the sentiment analysis engine will recognize frustration and automatically store related documents and materials in a "Frustration" folder.

[0597] As a concrete example, consider the case where a user types "I'm looking for marketing materials for a new product." The device sends this query to the server. The server uses Elasticsearch to search for relevant marketing materials and generates results in order of relevance. At the same time, the server uses IBM Watson's sentiment analysis API to analyze the emotion of "anticipation." The server displays the search results in a list on the user's device and automatically stores related documents in an "anticipation" folder. The user can select the materials they need from the displayed list and view them.

[0598] Examples of prompts include:

[0599] "I'm looking for marketing materials for a new product."

[0600] I can't find the sales report

[0601] "I'm looking for a document that summarizes customer feedback."

[0602] In this way, the server can provide the information the user needs quickly and efficiently.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The user enters a search query.

[0606] The user enters the required information into the device's search bar, for example, "I'm looking for marketing materials for a new product." The entered search query becomes the input data for the next step.

[0607] Step 2:

[0608] The device sends a search query to the server.

[0609] The device sends the search query entered by the user to the server. This communication uses an HTTP request. The sent search query becomes the server's input data.

[0610] Step 3:

[0611] The server uses a search engine to generate search results.

[0612] The server passes the received search query to a search engine such as Apache Solr or Elasticsearch to search for relevant documents and materials. The search engine returns relevant results from its indexed database. The search results serve as input data for the next step.

[0613] Step 4:

[0614] The server analyzes the user's emotions using an emotion analysis engine.

[0615] The server uses IBM Watson or Microsoft Azure sentiment analysis APIs to analyze emotions from user search queries. For example, from a query like "I'm looking for marketing materials for a new product," it can recognize emotions such as "expectation" and "excitement." The analyzed emotions become input data for the next step.

[0616] Step 5:

[0617] The server displays the search results in a list format in order of relevance.

[0618] The server sorts the results returned by the search engine in order of relevance and displays them in a list format on the user's device. The user can then select the documents or materials they need from this list. The displayed search results become the input data for the next step.

[0619] Step 6:

[0620] The server organizes documents and materials based on emotions.

[0621] The server automatically stores related documents and materials in specific folders and directories based on the emotions analyzed by the emotion analysis engine. For example, if the emotion of "expectation" is recognized, related documents are stored in the "expectation" folder. The organized documents and materials become input data for the next step.

[0622] Step 7:

[0623] The user selects the documents and materials they need.

[0624] The user selects the documents or materials they need from the displayed list of search results. The selected documents or materials are either downloaded to the user's device or displayed in a viewable format. The selected documents or materials become the final output data.

[0625] (Application example 2)

[0626] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0627] When employees cannot quickly find the documents and materials they need, it can lead to reduced work efficiency and increased stress. Furthermore, the quality of work can decline if appropriate support is not provided based on the employee's emotional state. In particular, in workplaces such as factories, quick and accurate searches for work instructions and manuals are required, but current systems do not adequately achieve this.

[0628] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0629] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion engine and organizing the documents and materials based on the analyzed results, and means for sorting relevant documents and materials according to the employee's emotions and providing detailed explanations and videos as needed. This allows employees to quickly find the information they need and provides appropriate support according to their emotional state, thereby improving work efficiency and reducing stress.

[0630] A "natural language processing engine" is a technology that analyzes employee questions and keywords and searches for related documents and materials.

[0631] "Search results" are a list of documents and materials searched by the natural language processing engine.

[0632] The "emotion engine" is a technology that analyzes employees' emotional context and organizes documents and materials based on that.

[0633] "Emotional context" is the emotional state inferred from the questions and keywords entered by the employee.

[0634] "Sorting" means arranging documents or materials based on specific criteria.

[0635] "Elaboration" means providing additional information or specific steps to a document or resource.

[0636] "Video" refers to video content that provides information visually.

[0637] A "folder" is a virtual storage location for organizing documents and materials.

[0638] A "directory" is a structure for organizing files and folders in a computer system.

[0639] A system for implementing this invention has the following configuration: The server includes a natural language processing engine, an emotion engine, a document search engine, and a database. The terminal includes a voice input device, a display, and an interface. A user accesses the system through the terminal and inputs questions or keywords.

[0640] The server first uses a natural language processing engine to analyze the question and keywords entered by the user. Based on this analysis, a document search engine searches the database for relevant documents and materials. The search results are sorted in order of relevance and provided to the user.

[0641] The emotion engine then analyzes the emotional context from the user's input. For example, if the user types, "I don't know how to install this part," the emotion engine recognizes the user's frustration. Based on this emotional context, the server further sorts relevant documents and resources, providing detailed instructions or videos as needed.

[0642] For example, consider a factory worker typing, "I don't know how to install this part." In this case, the server searches for relevant manuals, and if the emotion engine recognizes the worker's frustration, it provides detailed instructions and videos. This allows the worker to quickly obtain the information they need, improving work efficiency.

[0643] An example of a prompt to input to a generative AI model is as follows:

[0644] Create a program that analyzes the sentiment of employees when they type the phrase "I don't know how to install this part" and searches for and displays relevant documents and manuals. If employees are frustrated, provide detailed instructions or videos as well.

[0645] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0646] Step 1:

[0647] The user inputs a question or keyword through the terminal.

[0648] Input: The user enters a question or keyword by voice or text.

[0649] Output: The device sends the entered question or keyword to the server.

[0650] Step 2:

[0651] The server uses a natural language processing engine to analyze the user's questions and keywords.

[0652] Input: Questions or keywords sent from the device.

[0653] Data processing: A natural language processing engine uses machine learning models to analyze the meaning of questions and keywords.

[0654] Output: Keywords and phrases as analysis results.

[0655] Step 3:

[0656] The server uses a document search engine to search a database for relevant documents and materials based on the analysis results.

[0657] Input: Analysis results of the natural language processing engine.

[0658] Data calculation: A document search engine searches through documents and materials in a database and lists them in order of relevance.

[0659] Output: A list of relevant documents and materials.

[0660] Step 4:

[0661] The server sends the search results to the terminal, which then provides them to the user.

[0662] Input: List of relevant documents and materials.

[0663] Output: The device displays the search results to the user.

[0664] Step 5:

[0665] The server uses an emotion engine to parse the emotional context from the user's input.

[0666] Input: User question or keywords.

[0667] Data processing: The emotion engine analyzes emotions from user input and identifies emotional context.

[0668] Output: Emotional context (e.g., frustration).

[0669] Step 6:

[0670] The server re-sorts relevant documents and materials based on emotional context, adding detailed descriptions and videos as needed.

[0671] Input: A list of documents and materials related to the emotional context.

[0672] Data operations: Re-sorting documents and materials based on emotional context, adding detailed descriptions and videos.

[0673] Output: A re-sorted list of documents and resources, plus additional explanations and videos.

[0674] Step 7:

[0675] The server sends the re-sorted list of documents and materials, along with additional explanations and videos, to the terminal, which then provides them to the user.

[0676] Input: A re-sorted list of documents and materials, plus additional explanations and videos.

[0677] Output: The device displays the re-sorted document or material to the user, along with any additional instructions or videos.

[0678] Example 3

[0679] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0680] Employees have difficulty quickly and efficiently searching and organizing the documents and materials they need. This can be especially true when employees are under emotional stress.

[0681] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for searching for related documents and materials based on the employee's question or keywords using a natural language processing engine, means for analyzing the emotional context of the employee's question or keywords using an emotion engine, means for providing the search results to the employee, and means for organizing the documents and materials based on the search results. This enables employees to quickly and efficiently search for the documents and materials they need and organize information while reducing emotional stress.

[0682] A "natural language processing engine" is software that analyzes employee questions and keywords, understands their meaning, and searches for related documents and materials.

[0683] An "emotion engine" is software that analyzes the emotional context contained in employees' questions and keywords and recognizes their emotional state.

[0684] "Searching means" is a function that uses a natural language processing engine to search a database for relevant documents and materials based on an employee's questions or keywords.

[0685] "Means of provision" refers to the function of displaying search results to employees and enabling them to access the necessary documents and materials.

[0686] "Organizing means" is a function that categorizes documents and materials based on search results and automatically stores them in folders or directories corresponding to each category.

[0687] A "machine learning model" is an algorithm that learns from data and is used by natural language processing engines to analyze questions and keywords.

[0688] "Categorization" is the process of classifying and organizing documents and materials based on specific criteria.

[0689] A "folder or directory" is a digital repository for storing documents or materials.

[0690] MODE FOR CARRYING OUT THE INVENTION

[0691] The present invention is a system for enabling employees to quickly and efficiently search for and organize documents and materials they need. A specific embodiment of this system will be described below.

[0692] System configuration

[0693] This system consists of three main components: a server, a terminal, and a user. The server is equipped with a natural language processing engine and an emotion engine, and is responsible for analyzing user input and searching and organizing related documents and materials. The terminal provides an interface for users to access the system and input questions and keywords.

[0694] Hardware and software used

[0695] Natural Language Processing Engine: Use natural language processing software such as the Google Cloud Natural Language API.

[0696] Sentiment engine: Uses sentiment analysis software such as IBM Watson Tone Analyzer.

[0697] Database: Use a database system to store documents and materials, such as a SQL database or a NoSQL database.

[0698] Data processing and calculation

[0699] The server receives questions and keywords entered by the user through their device. The received input is first analyzed by a natural language processing engine. This analysis allows the meaning of the entered keywords and question to be understood, and relevant documents and materials are searched for in a database. At the same time, an emotion engine analyzes the emotional context contained in the user's input and recognizes the user's emotional state.

[0700] Based on the analysis results, the server selects the most relevant documents and materials and categorizes them. Categorized documents and materials are automatically stored in folders or directories corresponding to their categories. For example, documents related to the "Sales Report" category are stored in the "Sales Report" folder.

[0701] Specific examples

[0702] If the user inputs "I can't find the latest sales report" into the terminal, the process will proceed as follows:

[0703] 1. The user types "I can't find the latest sales report" into the terminal.

[0704] 2. The device sends this input to the server via an HTTP request.

[0705] 3. The server uses the Google Cloud Natural Language API to analyze "latest sales report" as a keyword.

[0706] 4. The server uses IBM Watson Tone Analyzer to recognize the user's frustration from the phrase "not found."

[0707] 5. The server searches the database for documents related to "sales reports."

[0708] 6. The server automatically stores the search results in the "Sales Report" folder.

[0709] 7. The server generates a link to the organized document and sends it back to the device.

[0710] 8. The user clicks on the link sent back via the device to access the organized "Sales Report."

[0711] Prompt Sentence Examples

[0712] "I can't find my latest sales report. Please find relevant documents and organize them into a sales report folder."

[0713] This system allows users to quickly and efficiently search and organize the information they need. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0714] Step 1:

[0715] The user enters a question or keyword into the device, for example, "I can't find the latest sales report." The entered data is sent to the server through the device's interface.

[0716] Step 2:

[0717] The terminal sends the input to the server. Specifically, it sends the user's input data to the server using an HTTP request. The input data is text data including the user's question and keywords.

[0718] Step 3:

[0719] The server analyzes the input data using a natural language processing engine. The server uses natural language processing software such as Google Cloud Natural Language API to analyze the meaning of the input question and keywords. As a result of the analysis, related keywords and phrases are extracted.

[0720] Step 4:

[0721] The server uses an emotion engine to analyze the emotional context. The server uses emotion analysis software such as IBM Watson Tone Analyzer to analyze the emotional state contained in the user's input. For example, the server recognizes the user's frustration from the phrase "I can't find it." The analysis results in the output emotional state.

[0722] Step 5:

[0723] The server searches the database for related documents and materials. Based on the analysis results of the natural language processing engine and emotion engine, the server searches the database for related documents and materials. A list of related documents and materials is output as the search results.

[0724] Step 6:

[0725] The server categorizes the search results and stores them in the corresponding folders. The server categorizes the search results into specific categories and automatically stores them in folders or directories corresponding to each category. For example, documents related to the "Sales Report" category are stored in the "Sales Report" folder. A list of categorized documents and materials is output.

[0726] Step 7:

[0727] The server returns links to the organized documents and materials to the terminal. The server generates links to the categorized documents and materials and returns them to the terminal as an HTTP response. The returned links are output in a format that the user can access.

[0728] Step 8:

[0729] Users access organized documents and materials through their devices. Users click on links displayed on their devices to access organized documents and materials. This allows users to quickly and efficiently obtain the information they need.

[0730] (Application example 3)

[0731] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0732] The problem is that it is difficult for employees to efficiently search and organize large amounts of documents and materials. In addition, search results are provided without taking into account the emotional context of employees, which can make it difficult to quickly find the information they need. In particular, in environments such as logistics centers, where document and material management is cumbersome, efficient search and organization are required.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0734] In this invention, the server includes means for using a natural language processing engine to search for relevant documents and materials based on employee questions and keywords, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion analysis engine to provide more relevant documents and materials, and means for categorizing the search results and automatically storing them in folders or directories corresponding to each category, thereby enabling employees to quickly and efficiently search for and organize the information they need.

[0735] A "natural language processing engine" is a technology that analyzes employee questions and keywords and searches for related documents and materials.

[0736] An "emotion analysis engine" is a technology that analyzes the emotional context based on employee input and provides more relevant documents and materials.

[0737] "Search results" refers to a collection of documents or materials searched by a natural language processing engine.

[0738] "Categorization" is the process of classifying search results into specific categories and automatically storing them in folders or directories corresponding to each category.

[0739] A "folder or directory" is a digital storage location for organizing and storing documents and materials.

[0740] "Employee" refers to a user who uses the system to search and organize documents and materials.

[0741] A "machine learning model" is an algorithm that learns from data and improves the performance of natural language processing engines and sentiment analysis engines.

[0742] "Documents and materials" is a general term for text and digital files containing information related to work.

[0743] The system for implementing the present invention includes a natural language processing engine, a sentiment analysis engine, and a function for categorizing search results and automatically storing them in folders. Specific embodiments are described below.

[0744] System Configuration

[0745] The server uses a natural language processing engine to search for relevant documents and materials based on the employee's questions and keywords. The sentiment analysis engine analyzes the emotional context based on the employee's input to provide more relevant documents and materials. Search results are categorized and automatically stored in folders and directories corresponding to each category.

[0746] Hardware and software used

[0747] Hardware: Smartphones, servers

[0748] Software: Python, Transformers library

[0749] Data processing and calculation

[0750] The server receives questions and keywords entered by employees using their smartphones. The natural language processing engine analyzes the entered text and searches the database for relevant documents and materials. The sentiment analysis engine analyzes the emotional context of the entered text to improve the relevance of search results. Search results are categorized and automatically stored in corresponding folders and directories.

[0751] Specific examples

[0752] If an employee uses their smartphone to type, "I can't find the latest sales report," the sentiment analysis engine will interpret their frustration. The natural language processing engine will search for documents related to "sales report," categorize them, and store them in folders. This allows employees to quickly and efficiently find and organize the information they need.

[0753] Prompt Sentence Examples

[0754] I can't find the latest sales report.

[0755] When this prompt is entered, the sentiment analysis engine analyzes the frustration, and the natural language processing engine searches for documents related to "sales reports," categorizes them, and stores them in folders.

[0756] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0757] Step 1:

[0758] A user enters a question or keyword using a smartphone.

[0759] Input: A question or keyword entered by the user (e.g., "I can't find the latest sales report")

[0760] Output: The input text data

[0761] Step 2:

[0762] The server receives the input text data and passes it to the natural language processing engine.

[0763] Input: Text data received from the user

[0764] Output: Text data passed to the natural language processing engine

[0765] Step 3:

[0766] A natural language processing engine analyzes the text data and searches the database for relevant documents and materials.

[0767] Input: Text data passed to the natural language processing engine

[0768] Output: List of relevant documents and materials

[0769] Step 4:

[0770] The server passes the text data to a sentiment analysis engine to analyze the emotional context.

[0771] Input: Text data passed to the natural language processing engine

[0772] Output: Sentiment analysis result (e.g., frustration)

[0773] Step 5:

[0774] Based on the results of the sentiment analysis engine, the server selects highly relevant documents and materials.

[0775] Input: Sentiment analysis results and a list of related documents and materials

[0776] Output: A list of relevant documents and resources

[0777] Step 6:

[0778] The server categorizes related documents and materials and automatically stores them in folders and directories corresponding to each category.

[0779] Input: A list of relevant documents and materials

[0780] Output: Folders or directories containing categorized documents and materials

[0781] Step 7:

[0782] The server provides the user with search results and notifies them of the folders in which relevant documents and materials are stored.

[0783] Input: Categorized document and resource information

[0784] Output: Search results and folder information provided to the user

[0785] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0786] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0788] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0789] [Second embodiment]

[0790] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0791] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0792] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure.

[0793] The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0794] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0795] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0796] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0797] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0798] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0799] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0800] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0801] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0802] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0803] "Example 1"

[0804] In one embodiment of the present invention, the natural language processing engine analyzes employee questions and keywords based on machine learning models. Specifically, when an employee enters a keyword such as "latest sales report," the natural language processing engine analyzes the keyword and searches a database for related documents and materials.

[0805] "Example 2"

[0806] The search results are provided to employees. Specifically, the search results are displayed in a list format, allowing employees to select the documents and materials they need. The search results are also displayed in order of relevance, allowing employees to quickly find the information they need.

[0807] "Example 3"

[0808] Furthermore, documents and materials are organized based on the search results. Specifically, search results are categorized and automatically stored in folders or directories corresponding to each category. For example, if there is a category called "Sales Reports," documents and materials related to this category will be automatically stored in the "Sales Reports" folder. This allows employees to efficiently search for and organize the information they need.

[0809] The processing flow of each embodiment will be described below.

[0810] "Example 1"

[0811] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[0812] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[0813] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[0814] "Example 2"

[0815] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[0816] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[0817] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[0818] Step 4: The selected documents and materials will be automatically stored in folders or directories corresponding to their categories. For example, if there is a category called "Sales Reports", documents and materials related to this category will be automatically stored in the "Sales Reports" folder.

[0819] Example 1

[0820] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0821] For employees to perform their work efficiently, it is important to be able to quickly search and retrieve the documents and materials they need. However, with conventional systems, keyword searches were inaccurate, and it often took a long time to find relevant documents and materials. In addition, the search results were manually organized, which was inefficient and prone to errors. To solve these issues, a system with more accurate search functions and automatic organization functions was needed.

[0822] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0823] In this invention, the server includes: means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine; means for providing the search results to the employee; means for organizing the documents and materials based on the search results; means for the employee to input keywords from a terminal; means for the terminal to transmit the input keywords to the server; means for the server to pass the keywords to the natural language processing engine; means for the natural language processing engine to analyze the keywords; means for the server to search a database based on the analysis results; means for the server to return search results to the terminal; and means for the terminal to display the search results to the employee. This allows employees to quickly and accurately search for and obtain the documents and materials they need. Furthermore, the automatic organization of search results improves work efficiency and reduces errors.

[0824] A "natural language processing engine" is software that uses machine learning models to analyze human language and understand its meaning.

[0825] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[0826] A "question" is an inquiry that an employee enters to obtain information.

[0827] "Keywords" are words or phrases that employees enter to search for specific information.

[0828] "Documents" are materials such as text files and reports that contain information related to business.

[0829] "Materials" are data and documents that contain information related to business.

[0830] A "searching means" is a method for identifying relevant documents or materials using a natural language processing engine.

[0831] The "means of providing" is the method for displaying the search results to employees.

[0832] "Organization methods" are methods for categorizing documents and materials based on search results and storing them in appropriate folders or directories.

[0833] "Terminals" are devices used by employees, such as computers and smartphones.

[0834] A "server" is a computer system that receives and processes requests from terminals.

[0835] A "database" is a collection of information in which documents and materials are stored.

[0836] "Means of analysis" refers to a method of using a natural language processing engine to understand the meaning of keywords and extract related information.

[0837] "Search Results" means a list of relevant documents or materials identified by a natural language processing engine.

[0838] "Display means" refers to a method for visually displaying search results on a terminal.

[0839] This invention is a system for quickly searching and retrieving documents and materials necessary for employees to perform their work efficiently. This system has the function of analyzing employee questions and keywords using a natural language processing engine and searching a database for related documents and materials.

[0840] Hardware and software used

[0841] Hardware

[0842] Server: A powerful computer system that manages databases and runs natural language processing engines.

[0843] Devices: These are devices used by employees, such as computers and smartphones.

[0844] software

[0845] Natural language processing engine: Uses machine learning models (e.g., BERT and GPT-3) to analyze employee questions and keywords.

[0846] Database: A collection of information in which documents and materials are stored, for example using MySQL.

[0847] Data processing and calculation

[0848] The server receives keywords entered by employees on their devices and sends them to a natural language processing engine. The natural language processing engine uses a machine learning model to analyze the keywords and extract information to identify related documents and materials. The server searches a database based on the analysis results and retrieves related documents and materials. The retrieved search results are returned from the server to the device and displayed for the employee to view.

[0849] Specific examples

[0850] As a concrete example, consider the case where an employee inputs the "latest sales report." In this case, the server performs the following process.

[0851] 1. The user types "Latest sales report" into the input field on the terminal.

[0852] 2. The device sends the keyword to the server using an HTTP POST request.

[0853] 3. The server passes the keywords to a natural language processing engine.

[0854] 4. The natural language processing engine uses the BERT model to parse the "latest sales report."

[0855] 5. The server uses the analysis results to search the MySQL database and identify the latest sales report.

[0856] 6. The server returns the search results to the device in JSON format.

[0857] 7. The terminal displays the search results to the user, allowing the user to view the latest sales report.

[0858] Prompt Sentence Examples

[0859] Below is an example of a prompt that the user might enter:

[0860] "View the latest sales report."

[0861] "Please tell me your sales data for 2023."

[0862] "Look for marketing materials for new products."

[0863] In this way, the user can easily obtain the information he or she needs.

[0864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] The user inputs a keyword from the terminal.

[0867] Specifically, the user inputs a keyword such as "latest sales report" into an input field on the terminal, and the input keyword is temporarily stored in the terminal's memory.

[0868] Input: The keyword entered by the user (e.g., "latest sales report")

[0869] Output: Keywords saved on the device

[0870] Step 2:

[0871] The terminal sends the entered keyword to the server.

[0872] Specifically, the terminal uses an HTTP POST request to send the input keyword to the server, with the keyword included in the request body.

[0873] Input: Keywords saved on your device

[0874] Output: Keywords sent to the server

[0875] Step 3:

[0876] The server passes the keywords to a natural language processing engine.

[0877] Specifically, the server passes the received keywords to the natural language processing engine, where the keywords are passed as parameters in the API request.

[0878] Input: The keyword sent to the server

[0879] Output: Keywords passed to the natural language processing engine

[0880] Step 4:

[0881] A natural language processing engine analyzes keywords.

[0882] Specifically, natural language processing engines use machine learning models (e.g., BERT or GPT-3) to analyze keywords, generating information that can be used to identify related documents and resources.

[0883] Input: Keywords passed to the natural language processing engine

[0884] Output: Analysis results (information on related documents and materials)

[0885] Step 5:

[0886] The server searches the database based on the analysis results.

[0887] Specifically, the server searches a database (e.g., MySQL) based on the analysis results. A search query is generated based on the analysis results and executed against the database.

[0888] Input: Analysis results

[0889] Output: Search results (related documents and materials) retrieved from the database

[0890] Step 6:

[0891] The server returns the search results to the device.

[0892] Specifically, the server returns the search results obtained from the database to the terminal in JSON format, etc., as an HTTP response.

[0893] Input: Search results retrieved from the database

[0894] Output: Search results sent to your device

[0895] Step 7:

[0896] The terminal displays the search results to the user.

[0897] Specifically, the terminal displays the search results received from the server on the user interface, for example, displaying a link to the latest sales report and a preview of its contents.

[0898] Input: Search results sent to your device

[0899] Output: Search results (related documents and resources) displayed to the user

[0900] (Application example 1)

[0901] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0902] Logistics centers face the challenge of making it difficult for employees to quickly obtain the information they need. In particular, there is a lack of efficient ways to search for and provide information such as inventory status, delivery schedules, and the location of items in the warehouse. This can lead to reduced operational efficiency, delays, and errors.

[0903] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0904] In this invention, the server includes means for searching for related documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing questions entered by the employee via voice or text and searching for related information from a database, and means for displaying the search results on a smartphone, thereby enabling employees to quickly obtain the information they need and improving work efficiency.

[0905] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0906] A "machine learning model" is an algorithm that learns from data and analyzes questions and keywords.

[0907] A "database" is a collection of data structured to allow efficient searching and retrieval of related information.

[0908] A "smartphone" is a portable electronic device that analyzes questions entered via voice or text and displays search results.

[0909] "Search results" are relevant information retrieved from a database based on the question or keywords analyzed by the natural language processing engine.

[0910] "Documents and materials" are any collection of text or data that contains information employees need.

[0911] "Categorization" is the process of classifying documents and materials based on search results and automatically storing them in folders or directories corresponding to their categories.

[0912] "Questions entered via voice or text" are inquiries entered by employees via their smartphones in voice or text format.

[0913] "Related information" refers to the necessary data and materials searched from the database in response to an employee's question or keyword.

[0914] A system for implementing this invention includes a natural language processing engine, a machine learning model, a database, and a smartphone. The specific configuration and operation of the system will be described below.

[0915] System configuration

[0916] 1. Natural language processing engine: Software that analyzes questions and keywords entered by employees and searches for relevant documents and materials. Specifically, it uses a natural language processing library such as spaCy.

[0917] 2. Machine learning model: An algorithm used to analyze questions and keywords. It is built using a machine learning library such as scikit-learn.

[0918] 3. Database: A structured collection of data for efficient searching and retrieval of related information. Use a database management system such as SQLite.

[0919] 4. Smartphone: A handheld electronic device that allows employees to enter questions by voice or text and display search results. iOS or Android smartphones are used.

[0920] System Operation

[0921] 1. User input: An employee uses a smartphone to input a question in voice or text format. For example, they input a prompt such as "Please tell me the latest inventory status."

[0922] 2. Natural Language Processing: The server uses a natural language processing engine to analyze the user's input and extract keywords, such as "stock status" and "latest."

[0923] 3. Database search: The server searches the database based on the extracted keywords to retrieve relevant documents and materials, for example, documents containing the latest inventory information.

[0924] 4. Providing search results: The server sends the search results to the smartphone and displays them to the user, allowing employees to quickly obtain the information they need.

[0925] Specific examples

[0926] When an employee types "Please tell me the latest inventory status" into their smartphone, the natural language processing engine extracts keywords such as "inventory status" and "latest" and searches the database for the latest inventory information. As a result, the latest inventory information is displayed on the smartphone.

[0927] Other example prompts might include questions such as "What is the latest delivery schedule?" or "Where are the items located in the warehouse?"

[0928] This system allows employees to quickly obtain the information they need, improving work efficiency.

[0929] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0930] Step 1:

[0931] The user inputs a question in voice or text format using a smartphone.

[0932] Input: A user's voice or text question (e.g., "What is the latest inventory status?")

[0933] Output: Question data entered into a smartphone

[0934] How it works: A user launches an application on their smartphone and uses voice or text input. In the case of voice input, the speech recognition software converts the speech into text.

[0935] Step 2:

[0936] The server uses a natural language processing engine to analyze the user's input and extract keywords.

[0937] Input: User's question data (text format)

[0938] Output: Extracted keywords (e.g., "Availability", "Latest")

[0939] How it works: The server uses a natural language processing library such as spaCy to analyze the text and extract important keywords, for example, by performing morphological analysis to identify important words such as nouns and verbs.

[0940] Step 3:

[0941] The server searches the database based on the extracted keywords to retrieve related documents and materials.

[0942] Input: Extracted keywords (e.g., "inventory status," "latest")

[0943] Output: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[0944] Specific operation: The server uses a database management system such as SQLite to search for documents or materials that match the keywords, for example, by executing an SQL query to retrieve records that match the keywords.

[0945] Step 4:

[0946] The server sends the search results to the smartphone and displays them to the user.

[0947] Input: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[0948] Output: Search results displayed on a smartphone

[0949] Specific operation: The server converts the search results into a data format such as JSON and sends it to the smartphone. The smartphone application analyzes the received data and displays it in a format that is easy for the user to view.

[0950] Step 5:

[0951] The user checks the search results displayed on the smartphone and obtains the information they need.

[0952] Input: Search results displayed on smartphone

[0953] Output: The information the user needs (e.g., the latest inventory information)

[0954] Specific operation: The user checks the search results displayed on the smartphone screen and obtains the necessary information, such as stock availability and delivery schedules.

[0955] Example 2

[0956] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0957] Employees need to be able to search for the documents and materials they need quickly and efficiently, and to receive results organized in order of relevance. However, with conventional systems, search results were not properly organized, making it time-consuming to find the information they needed. Furthermore, the display format of search results was inappropriate, making it difficult for users to quickly find the information they needed.

[0958] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0959] In this invention, the server includes means for searching for documents and materials related to employee questions and keywords using a natural language processing engine, means for sorting the search results in descending order of relevance, and means for generating a list of the search results, thereby enabling employees to quickly and efficiently find the information they need.

[0960] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[0961] "Searching tools" is the ability to find documents and materials in the database based on employee questions or keywords.

[0962] The "means of providing" is the function for displaying search results to employees.

[0963] "Sorting means" is a function for organizing search results in order of relevance.

[0964] The "means for generating" is a function for formatting search results in a list format.

[0965] The "display means" is a function for displaying the generated search results on the employee's terminal.

[0966] A "machine learning model" is an algorithm that analyzes questions and keywords based on data.

[0967] "Categorization means" is a function that categorizes search results based on specific criteria and automatically stores them in folders or directories corresponding to each category.

[0968] MODE FOR CARRYING OUT THE INVENTION

[0969] The present invention is a system that enables employees to quickly and efficiently search for documents and materials they need, and provides results organized in order of relevance. Specific embodiments of this system are described below.

[0970] System configuration

[0971] The system consists of three main components: a server, a terminal, and a user. The server uses a natural language processing engine and machine learning models to analyze search queries and retrieve relevant documents and materials. The terminal is a device where users input search queries and display search results. The user is an employee who uses the system to search for the information they need.

[0972] Hardware and software used

[0973] Server: Use a computer system with a high-performance processor and large memory capacity. On the server, install a Python-based library (e.g., NLTK, spaCy) as a natural language processing engine, and use Elasticsearch as the search algorithm.

[0974] Terminal: A device used by a user, such as a PC or smartphone, on which a web browser and dedicated applications are installed.

[0975] Software: We use machine learning models (e.g., BERT, GPT) to analyze search queries, which allows us to analyze user questions and keywords with high accuracy.

[0976] System Operation

[0977] 1. User enters a search query

[0978] The user enters the required information into the device's search bar, for example, "project report."

[0979] 2. The device sends the search query to the server

[0980] The device sends the search query entered by the user to the server using an HTTP request.

[0981] 3. The server receives the search query and queries Elasticsearch

[0982] The server analyzes the search query received from the terminal and sends a search request to Elasticsearch.

[0983] 4. The server receives the search results from Elasticsearch

[0984] The server receives search results returned from Elasticsearch, which contain relevant document and resource information.

[0985] 5. The server sorts the search results by relevance.

[0986] The server sorts the received search results in order of relevance, using Elasticsearch's scoring function to evaluate relevance.

[0987] 6. The server generates a list of search results

[0988] The server formats the sorted search results into a list in HTML format.

[0989] 7. The server sends the search results to the device.

[0990] The server sends the generated search results in HTML format to the terminal using an HTTP response.

[0991] 8. The device displays the search results to the user.

[0992] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format.

[0993] 9. The user selects the documents and materials they need.

[0994] Users can select the documents or materials they need from the displayed search results, and click on the selected document to display details.

[0995] Specific examples

[0996] As a concrete example, consider the case where a user searches for "project report." The user enters "project report" into the terminal and clicks the search button. The server receives this query and uses Elasticsearch to search for documents in the database. The search results are sorted in order of relevance and displayed to the user in a list format. The user can then select the document they need from this list.

[0997] Prompt Sentence Examples

[0998] An example of a prompt sentence might be:

[0999] Prompt: "Find project reports"

[1000] When this prompt is input into the generative AI model, the AI ​​model will provide search results to help employees quickly find the project report they need.

[1001] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1002] Step 1:

[1003] The user enters a search query.

[1004] The user enters the required information into the device's search bar, for example, "project report," and the query is temporarily stored in the device's memory.

[1005] Step 2:

[1006] The device sends a search query to the server.

[1007] The device sends the search query entered by the user to the server as an HTTP request. This request includes the query entered by the user. After sending the request, the device waits for a response from the server.

[1008] Step 3:

[1009] The server receives the search query and queries Elasticsearch.

[1010] The server analyzes the search query received from the device and sends a search request to Elasticsearch. Specifically, the server passes the search query to Elasticsearch's API, instructing it to search for related documents and materials. The input is the search query, and the output is the search results from Elasticsearch.

[1011] Step 4:

[1012] The server receives the search results from Elasticsearch.

[1013] The server receives the search results returned from Elasticsearch. The search results contain information about related documents and resources. The server stores the results in memory for further processing. The input is the search results from Elasticsearch, and the output is the search results stored in the server's memory.

[1014] Step 5:

[1015] The server sorts the search results by relevance.

[1016] The server uses Elasticsearch's scoring function to sort the received search results in order of relevance. Specifically, it calculates the relevance score of each document and sorts them in order of highest to lowest. The input is the search results stored in the server's memory, and the output is the sorted search results.

[1017] Step 6:

[1018] The server generates the search results in a list format.

[1019] The server formats the sorted search results into a list in HTML format. Specifically, it wraps the title and summary of each document in HTML tags to make it easier for users to view. The input is the sorted search results, and the output is the HTML-formatted search results.

[1020] Step 7:

[1021] The search results generated by the server are sent to the terminal.

[1022] The server generates the search results in HTML format and sends them to the terminal as an HTTP response. The input is the search results in HTML format, and the output is the search results sent to the terminal.

[1023] Step 8:

[1024] The terminal displays the search results to the user.

[1025] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format. Specifically, the web browser parses the HTML and displays it on the screen. The input is the HTML search results received from the server, and the output is the search results displayed to the user.

[1026] Step 9:

[1027] The user selects the documents and materials they need.

[1028] The user selects the necessary documents or materials from the displayed search results. Clicking on the selected document displays details. The input is the user's click operation, and the output is a detailed display of the selected document.

[1029] (Application example 2)

[1030] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1031] At logistics centers, employees are required to quickly search for necessary inventory and delivery information and carry out their work efficiently. However, with conventional systems, searching for information takes time and displays a lot of irrelevant information, resulting in reduced work efficiency. Furthermore, information search using smartphones is not fully utilized, making it difficult to respond quickly on-site.

[1032] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1033] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for displaying inventory information and delivery information in order of relevance, and means for employees to quickly search for necessary information using their smartphones, thereby enabling employees to quickly search for necessary information and improving work efficiency.

[1034] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1035] "Means for providing search results" refers to a function for displaying searched documents and materials to employees.

[1036] "Means for organizing documents and materials" refers to a function that categorizes documents and materials based on search results and automatically stores them in folders or directories corresponding to each category.

[1037] "A means for displaying inventory information and delivery information in order of relevance" is a function for sorting and displaying inventory data and delivery data in order of relevance based on a search query.

[1038] "Means for employees to quickly search for the information they need using their smartphones" refers to a function that allows employees to quickly search for the information they need using their smartphones.

[1039] A system for carrying out the present invention enables employees at a logistics center to quickly search for necessary inventory information and delivery information. A specific embodiment of this system will be described below.

[1040] System configuration

[1041] The system consists of the following main components:

[1042] 1. Server: Equipped with a natural language processing engine and machine learning models, it analyzes employee questions and keywords.

[1043] 2. Smartphone: Enter a search query on the employee's device and view the search results.

[1044] 3. Database: Stores inventory and shipping information.

[1045] Program processing

[1046] The server works as follows:

[1047] 1. Natural language processing engine: Analyzes questions and keywords entered by employees on their smartphones and searches for relevant documents and materials.

[1048] 2. Machine learning models: Generate search results in order of relevance based on an analysis of the question and keywords.

[1049] 3. Providing search results: Search results are sent to employees' smartphones and provided to them.

[1050] 4. Data organization: Documents and materials are categorized based on search results and automatically stored in folders and directories corresponding to each category.

[1051] 5. Display inventory and shipping information: Display inventory and shipping data sorted by relevance.

[1052] Hardware and software used

[1053] Hardware: Smartphones, servers

[1054] Software: Python, Pandas, Scikit-learn, natural language processing engine (e.g., SpaCy)

[1055] Specific examples

[1056] When an employee searches for "out of stock items," the system works as follows:

[1057] 1. An employee types "out of stock item" into their smartphone.

[1058] 2. The server's natural language processing engine parses the query and searches for relevant inventory information.

[1059] 3. The machine learning model generates search results in order of relevance.

[1060] 4. Search results are displayed on a smartphone, allowing employees to see a list of items that are out of stock.

[1061] Prompt Sentence Examples

[1062] Search query: "out of stock items"

[1063] In this way, logistics center employees can quickly find the information they need and improve work efficiency.

[1064] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1065] Step 1:

[1066] A user types a search query into their smartphone.

[1067] Input: A user types "item out of stock" into their smartphone.

[1068] Output: The search query is sent to the server.

[1069] Specific operation: The user enters "out of stock items" into the search bar on their smartphone and presses the search button.

[1070] Step 2:

[1071] The server analyzes the search query using a natural language processing engine.

[1072] Input: A search query sent from a smartphone: "Products out of stock."

[1073] Output: Parsed query data.

[1074] What it does: The server's natural language processing engine (e.g., SpaCy) tokenizes the search query and extracts key keywords.

[1075] Step 3:

[1076] The server uses machine learning models to search for relevant documents and materials.

[1077] Input: Parsed query data.

[1078] Output: A list of relevant documents and materials.

[1079] What it does: The server's machine learning model (e.g., Scikit-learn) uses the parsed query data to search for inventory and delivery information in the database and sort it by relevance.

[1080] Step 4:

[1081] The server sends the search results to the smartphone.

[1082] Input: List of relevant documents and materials.

[1083] Output: Search results displayed on a smartphone.

[1084] Specific operation: The server sends a list of relevant documents and materials to the smartphone and displays it to the user.

[1085] Step 5:

[1086] The user checks the search results on their smartphone.

[1087] Input: Search results displayed on a smartphone.

[1088] Output: The user confirms the required information.

[1089] Specific behavior: The user scrolls through the search results displayed on their smartphone screen and checks the necessary inventory and delivery information.

[1090] Step 6:

[1091] The server organizes documents and materials based on the search results.

[1092] Input: List of relevant documents and materials.

[1093] Output: Categorized documents and materials.

[1094] Specific operation: The server categorizes documents and materials based on the search results and automatically stores them in folders or directories corresponding to each category.

[1095] Step 7:

[1096] The server displays inventory and delivery information in order of relevance.

[1097] Input: Relevant inventory and shipping information.

[1098] Output: Stock and shipping information sorted by relevance.

[1099] Specific behavior: The server sorts inventory and shipping data in order of relevance and displays it to the user.

[1100] Example 3

[1101] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1102] There is a problem that it is difficult for employees to efficiently search and organize the information they need. Especially when there are a large number of documents and materials, manual searching and organization takes time and effort, reducing work efficiency. In addition, if search results are not properly categorized, it is difficult to quickly find the information you need.

[1103] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for searching for relevant information based on the employee's question or keyword using a natural language processing engine, means for providing the employee with the search results, means for analyzing and categorizing information based on the search results, and means for automatically storing the categorized information in folders or directories corresponding to each category. This enables employees to efficiently search for and organize the information they need.

[1104] A "natural language processing engine" is software that analyzes natural language and understands its meaning.

[1105] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[1106] "Questions and keywords" are input data that employees use to search for information.

[1107] "Relevant information" refers to documents and materials retrieved based on an employee's question or keywords.

[1108] "Search methods" are methods and techniques for obtaining relevant information based on employee questions or keywords.

[1109] "Means of providing" refers to the methods and technologies used to display search results to employees.

[1110] "Means for analyzing and categorizing" refers to the methods and techniques used to analyze and categorize search results into specific categories.

[1111] "Folders and directories" are virtual storage locations for organizing information within a computer.

[1112] "Automatic storage means" refers to methods or techniques for automatically moving analyzed information into corresponding folders or directories.

[1113] A "machine learning model" is an algorithm that learns from data and makes predictions and classifications.

[1114] The present invention is a system for enabling employees to efficiently search for and organize necessary information. A specific embodiment of this system will be described below.

[1115] System configuration

[1116] This system consists of three main components: a server, a terminal, and a user.

[1117] 1. Server:

[1118] The server uses a natural language processing engine to search for relevant information based on employee questions and keywords. Specifically, it uses search engines such as Apache Solr and Elasticsearch. It also uses natural language processing tools such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding to analyze and categorize the search results. It then uses the Python os and shutil modules to automatically store the categorized information in the corresponding folders and directories.

[1119] 2. Terminal:

[1120] A terminal is a device on which a user inputs a search query and checks search results. Terminals include computing devices such as PCs, tablets, and smartphones.

[1121] 3. User:

[1122] Users are employees who use the system to search and organize information. Users use terminals to enter search queries and view organized information.

[1123] System Operation

[1124] 1. User enters a search query:

[1125] Users enter a question or keyword into the device's search bar, for example, "Sales report 2023."

[1126] 2. Server retrieves search results:

[1127] The server receives the search query entered by the user and retrieves relevant information from the database using Apache Solr or Elasticsearch.

[1128] 3. Server analysis and categorization of search results:

[1129] The server analyzes the search results using Google Cloud Natural Language API or IBM Watson Natural Language Understanding and categorizes them into appropriate categories, such as "sales reports," "financial reports," and "market analysis."

[1130] 4. Server stores files in folders by category:

[1131] The server automatically stores the categorized information in folders or directories corresponding to each category using the Python os and shutil modules. For example, information categorized as "Sales Report" is stored in the "Sales Report" folder.

[1132] 5. User review of organized information:

[1133] The user can use the device to view the organized folders, for example, by opening the "Sales Report" folder and viewing the information they need.

[1134] Examples of specific examples and prompts

[1135] Examples:

[1136] When a user searches for "Sales Report 2023", the specific operations are as follows:

[1137] 1. User: Enter "Sales Report 2023" into the device's search bar and click the search button.

[1138] 2. Server: Receives search queries and retrieves relevant information from the database using Apache Solr.

[1139] 3. Server: Analyze the acquired information using the Google Cloud Natural Language API and classify it into the "Sales Report" category.

[1140] 4. Server: Use Python's os module to move the classified information to the "Sales Report" folder.

[1141] 5. User: Open the "Sales Report" folder on the device and check the required information.

[1142] Example prompt sentence:

[1143] "Search for sales reports for 2023 and automatically store the relevant information in the sales reports folder."

[1144] This system allows users to efficiently search and organize the information they need. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1145] Step 1: User enters a search query

[1146] A user enters a question or keyword into the device's search bar. For example, they might enter "Sales Report 2023." The input data is text about the information the user wants to search for. The output is sent to the server as a search query.

[1147] Step 2: Server retrieves search results

[1148] The server receives a search query entered by a user and retrieves relevant information from a database using a search engine (e.g., Apache Solr or Elasticsearch). The input data is the user's search query. The server sends the search query to the search engine to retrieve relevant documents and materials. The output is a list of documents and materials as search results.

[1149] Step 3: Server analyzes and categorizes search results

[1150] The server analyzes the search results using a natural language processing engine (for example, Google Cloud Natural Language API or IBM Watson Natural Language Understanding). The input data are the documents and materials obtained as search results. The server analyzes these documents and classifies them into appropriate categories. For example, they could be categorized as "sales reports," "financial reports," or "market analysis." The output is a list of categorized documents and materials.

[1151] Step 4: The server stores the categories in folders

[1152] The server automatically stores categorized documents and materials in folders and directories corresponding to each category. The input data are categorized documents and materials. The server uses Python's os module and shutil module to obtain the document path and move it to the corresponding folder. For example, documents categorized in the "Sales Report" category are stored in the "Sales Report" folder. The output is the documents and materials stored in the folder.

[1153] Step 5: User reviews the organized information

[1154] The user uses a terminal to check the organized folders. The input data are the documents and materials stored in the folders. The user can open, for example, the "Sales Report" folder and view the necessary documents. The output is the documents and materials that the user views.

[1155] This system allows users to efficiently search and organize the information they need.

[1156] (Application example 3)

[1157] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1158] In conventional document management systems, searching and organizing documents and materials is often done manually, resulting in inefficiencies. Furthermore, many paper-based documents are used at logistics centers and other on-site locations, creating a need for a way to digitize and efficiently manage them. Furthermore, categorizing documents and uploading them to cloud storage is often done manually, which is time-consuming and labor-intensive.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1160] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for extracting text from images using optical character recognition technology, means for categorizing the documents based on the extracted text and automatically storing them in corresponding folders, and means for uploading the documents to cloud storage, thereby enabling efficient search, organization, digitization, and automatic uploading of documents and materials to cloud storage.

[1161] A "natural language processing engine" is software that analyzes natural language and searches for relevant information based on questions or keywords.

[1162] "Employee" refers to a person who belongs to a company or organization and performs work.

[1163] "Search methods" refer to methods and techniques for finding specific information.

[1164] "Means of delivery" refers to the methods and technologies used to display or make accessible search results to users.

[1165] "Organizational methods" refer to methods and techniques for classifying and managing documents and materials based on specific criteria.

[1166] "Optical character recognition technology" is a technology for extracting character information from images.

[1167] "Image" refers to a digital file containing visual information.

[1168] "Text" refers to digital data containing textual information.

[1169] "Categorization" refers to classifying information based on specific criteria.

[1170] A "folder" refers to a virtual container for organizing digital data.

[1171] "Cloud storage" refers to a remote server for storing data over the Internet.

[1172] "Upload" refers to the transfer of data from a local device to a remote server.

[1173] A system for implementing this invention is configured as follows: First, the server uses a natural language processing engine to search for relevant documents and materials based on the employee's question and keywords. The natural language processing engine analyzes the question and keywords based on a machine learning model. The analyzed results are provided to the employee.

[1174] The server then organizes the documents and materials based on the search results. To organize them, it uses optical character recognition (OCR) technology to extract text from images. The extracted text is then categorized based on specific keywords and automatically stored in corresponding folders. The documents are then uploaded to cloud storage.

[1175] To realize this system, the following hardware and software are used: A smartphone with a camera is required for the hardware, and Python, an OCR library, PIL (Python Imaging Library), and Google Cloud Storage are used for the software.

[1176] As a concrete example, consider a document organization app used in a logistics center. When an employee takes a photo of a shipping instruction sheet with their smartphone camera, the image is converted into text using OCR technology. The converted text is classified into a category called "Shipping Instructions" and automatically stored in the corresponding folder. The document is then uploaded to cloud storage.

[1177] An example of a prompt sentence might be:

[1178] "Please develop a document organization app to be used in a logistics center. This application will analyze document images taken with a smartphone camera using OCR technology, automatically classify them into categories such as shipping instructions, receipts, and inventory lists, and upload them to cloud storage."

[1179] In this way, documents and materials can be efficiently searched, organized, digitized and automatically uploaded to cloud storage.

[1180] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1181] Step 1:

[1182] The user takes a photo of the document using the smartphone camera.

[1183] Input: Paper-based document

[1184] Output: Digital image file

[1185] Specific operation: The user launches the smartphone's camera app and takes a photo of a document. The captured image is saved in the smartphone.

[1186] Step 2:

[1187] The device uses optical character recognition (OCR) technology to extract text from the image.

[1188] Input: Digital image file

[1189] Output: Extracted text data

[1190] Specific operation: The device inputs the saved image file into OCR software and extracts the text information in the image as text data.

[1191] Step 3:

[1192] The device analyzes the extracted text and categorizes it.

[1193] Input: Extracted text data

[1194] Output: Category information

[1195] Specific operation: The terminal analyzes the extracted text data and determines categories based on specific keywords (e.g., "shipping instructions," "receipt," etc.).

[1196] Step 4:

[1197] The terminal automatically stores the documents in the corresponding folders based on the categories.

[1198] Input: Category information, digital image files

[1199] Output: Documents stored in a folder

[1200] Specific operation: The terminal moves or copies the digital image files to the corresponding folders based on the determined categories.

[1201] Step 5:

[1202] The device uploads the document to cloud storage.

[1203] Input: Documents stored in a folder

[1204] Output: Documents saved in cloud storage

[1205] Specific operation: The device uploads the documents in the folder to a cloud storage service (Google Cloud Storage). Once the upload is complete, the documents are stored in the cloud.

[1206] Step 6:

[1207] The server uses a natural language processing engine to search for relevant documents and materials based on the employee's questions and keywords.

[1208] Input: Employee question or keyword

[1209] Output: Search results for related documents and resources

[1210] Specific operation: The server inputs the questions and keywords entered by the employee into a natural language processing engine to search for relevant documents and materials, and provides the search results to the employee.

[1211] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1212] "Example 1"

[1213] In one embodiment of the present invention, a natural language processing engine is combined with an emotion engine. When an employee enters a question or keywords into the system, the natural language processing engine analyzes the keywords and searches a database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question and keywords. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine recognizes the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[1214] "Example 2"

[1215] In another embodiment of the present invention, an emotion engine organizes documents and materials based on the employee's emotional context. Specifically, the emotion engine analyzes the employee's emotional context and automatically stores documents and materials in folders or directories corresponding to the respective emotional context. For example, if an employee types the phrase "I can't find the sales report," the emotion engine recognizes the employee's frustration from this phrase, and the system automatically stores the relevant documents and materials in a "Frustration" folder.

[1216] "Example 3"

[1217] In one embodiment of the present invention, a natural language processing engine is combined with an emotion engine. When an employee enters a question or keywords into the system, the natural language processing engine analyzes the keywords and searches a database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question and keywords. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine recognizes the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[1218] The processing flow of each embodiment will be described below.

[1219] "Example 1"

[1220] Step 1: An employee enters a question or keyword into the system.

[1221] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and materials.

[1222] Step 3: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[1223] Step 4: The natural language processing engine uses the results of the emotion engine's analysis to provide more relevant documents and materials.

[1224] "Example 2"

[1225] Step 1: An employee enters a question or keyword into the system.

[1226] Step 2: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[1227] Step 3: Based on the analysis results of the emotion engine, documents and materials are automatically stored in folders and directories that correspond to their emotional context.

[1228] Example 1

[1229] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1230] Conventional systems were unable to consider emotional context when searching for documents and materials related to questions or keywords entered by employees, making it difficult to fully meet employees' needs. Furthermore, the organization and provision of search results did not provide appropriate information that reflected employees' emotions, hindering efficient work execution.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1232] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the emotional context of the employee questions and keywords using an emotion engine, and means for providing highly relevant documents and materials based on the emotional context. This makes it possible to provide appropriate information that takes employee emotions into consideration, thereby improving work efficiency and employee satisfaction.

[1233] A "natural language processing engine" is software that analyzes questions and keywords entered by employees, understands their meaning, and searches for related documents and materials.

[1234] A "machine learning model" is an algorithm that learns from data and finds patterns and rules, and is used to improve the analytical capabilities of natural language processing engines.

[1235] The "emotion engine" is software that analyzes the emotional context contained in employees' questions and keywords and recognizes those emotions.

[1236] "Documents and materials" is a general term for texts, reports, presentations, data sheets, etc. that contain information employees need to perform their jobs.

[1237] A "database" is an information system for efficiently storing, searching, and managing documents and materials.

[1238] "Search Results" are a list of documents or materials retrieved from a database based on a question or keywords analyzed by a natural language processing engine and sentiment engine.

[1239] "Categorization" is the process of classifying documents or materials based on search results according to specific themes or attributes.

[1240] A "folder or directory" is a virtual storage location on a computer for organizing and storing documents and materials.

[1241] An "employee" is a user who uses the system to input questions or keywords to carry out work.

[1242] MODE FOR CARRYING OUT THE INVENTION

[1243] This invention is a system that analyzes questions and keywords entered by employees and provides relevant documents and materials. The system combines a natural language processing engine and an emotion engine to provide information that takes into account the employee's emotional context.

[1244] Hardware and software used

[1245] server

[1246] The server performs the main processing of the system using the following software:

[1247] Natural language processing engines (e.g., BERT, GPT-3)

[1248] Emotion engine (e.g., emotion analysis API)

[1249] Database management systems (e.g., MySQL, PostgreSQL)

[1250] Terminal

[1251] The terminal provides an interface for employees to enter questions or keywords. The terminal uses the following software:

[1252] Web browser or dedicated application

[1253] HTTP client library

[1254] User

[1255] The user (employee) enters a question or keyword into the system and checks the search results.

[1256] Data processing and calculation

[1257] Natural Language Processing Engine

[1258] The server passes the questions and keywords entered by employees to a natural language processing engine for analysis. The natural language processing engine uses machine learning models (e.g., BERT, GPT-3) to understand the meaning of the input text and extract keywords to search for related documents and materials.

[1259] Emotion Engine

[1260] The server passes the input text to an emotion engine that analyzes the emotional context. The emotion engine recognizes the employee's emotions (e.g., frustration, joy) from the input text and uses that information to provide relevant documents and resources.

[1261] Database search

[1262] The server uses the results of the natural language processing and emotion engines to search for relevant documents and materials from the database, and the search results are prioritized taking into account the employee's emotional context.

[1263] Providing and organizing results

[1264] The server sends the search results to the terminal, which displays them to the user. Furthermore, the terminal categorizes the documents and materials based on the search results and automatically stores them in folders and directories corresponding to each category.

[1265] Specific examples

[1266] If an employee types "I can't find the latest sales report," the device sends this input to the server. The server uses a natural language processing engine to analyze the keyword "latest sales report" and an emotion engine to recognize the employee's frustration from the phrase "I can't find it." The server uses this information to search for relevant documents in the database and sends the search results to the device. The device then displays the search results to the user.

[1267] Prompt Sentence Examples

[1268] "If an employee types into the system, 'I can't find the latest sales report,' how would the system respond?"

[1269] By feeding this prompt into a generative AI model, a response is obtained that details the system's behavior.

[1270] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1271] Step 1:

[1272] The user enters a question or keyword.

[1273] The user enters a question or keyword, such as "I can't find the latest sales report," into the system interface. The entered text is displayed in the input field on the device. Specific actions include the user entering text using the keyboard and clicking the send button.

[1274] Step 2:

[1275] The device sends input to the server.

[1276] The terminal sends the text entered by the user to the server. The input text is sent to the server as an HTTP request. Specifically, the terminal application generates an HTTP request and sends it to the server.

[1277] Step 3:

[1278] The server analyzes the input using a natural language processing engine.

[1279] The server passes the received text to a natural language processing engine for analysis. By analyzing the input text, related keywords and phrases are extracted. Specifically, the server calls the API of the natural language processing engine to obtain the analysis results. The input is the user's text, and the output is the analyzed keywords and phrases.

[1280] Step 4:

[1281] The server analyzes the emotional context with an emotion engine.

[1282] The server passes the input text to the emotion engine and analyzes the emotional context. The emotion engine recognizes the employee's emotion (e.g., frustration) from the input text. Specifically, the server calls the emotion engine's API to obtain the emotion analysis results. The input is the user's text, and the output is the analyzed emotional information.

[1283] Step 5:

[1284] The server searches the database for relevant documents and materials.

[1285] The server searches the database for relevant documents and materials based on the analysis results of the natural language processing engine and emotion engine. The search results are prioritized taking into account the employee's emotional context. Specifically, the server generates an SQL query and executes the search against the database. The input is the analysis result, and the output is a list of the retrieved documents and materials.

[1286] Step 6:

[1287] The server sends the search results to the terminal.

[1288] The server sends the search results to the terminal. The search results are sent to the terminal as an HTTP response. In concrete terms, the server generates an HTTP response and sends it to the terminal. The input is the search results, and the output is the data sent to the terminal.

[1289] Step 7:

[1290] The terminal displays the search results to the user.

[1291] The terminal displays the search results received from the server to the user, who can then check related documents and materials. Specifically, the terminal application displays the search results on the screen. The input is data from the server, and the output is the search results displayed to the user.

[1292] (Application example 1)

[1293] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1294] It is important for employees to be able to quickly and accurately search for and obtain the documents and materials they need within the factory. However, with conventional systems, it often took employees a long time to find the information they needed, reducing efficiency. Furthermore, providing information without taking into account the emotional state of employees can increase stress and frustration. To solve these problems, support that takes into account the emotional context is needed, rather than simply analyzing employees' questions and keywords and providing relevant documents and materials.

[1295] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1296] In this invention, the server includes means for searching for relevant documents and materials based on the employee's questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the emotional context of the employee's questions and keywords using a sentiment analysis engine, and means for providing additional support to the employee based on the emotional context, thereby enabling the employee to not only quickly and accurately obtain the information they need, but also receive emotional support.

[1297] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1298] A "machine learning model" is an algorithm that learns from data and analyzes employee questions and keywords.

[1299] A "sentiment analysis engine" is software that analyzes the emotional context of employee questions and keywords.

[1300] "Documents and materials" includes information such as manuals, work instructions, and reports used within the factory.

[1301] "Search Results" means a list of relevant documents or materials retrieved by a natural language processing engine.

[1302] "Categorization" is the process of classifying documents or materials into specific categories based on search results.

[1303] A "folder or directory" is a digital storage location for organizing and storing documents and materials.

[1304] "Additional support" is encouragement or additional information provided based on the emotional context analyzed by the sentiment analysis engine.

[1305] To implement this invention, the following hardware and software are used. The hardware includes a robot body used in a factory, a built-in microphone and speaker, and a display. The software includes a natural language processing engine (e.g., spaCy, BERT), a sentiment analysis engine (e.g., IBM Watson Tone Analyzer), a database management system (e.g., MySQL, PostgreSQL), and robot control software (e.g., ROS - Robot Operating System).

[1306] When an employee speaks a question or keyword to the robot, the server uses a built-in microphone to capture the voice and converts it into text using speech recognition software (e.g., Google Speech-to-Text API). A natural language processing engine then analyzes the converted text and extracts the keywords and intent of the question. For example, if an employee says, "Show me the latest work order," the server extracts the keyword "latest work order."

[1307] The sentiment analysis engine then analyzes the emotional context of the text. For example, if "I can't find the work instructions," it will detect frustration. The server then searches the database for relevant documents and materials based on the extracted keywords. For example, it retrieves documents related to "latest work instructions" from the database.

[1308] The search results are displayed on the screen and the employee is notified by voice. Based on the results of sentiment analysis, words of encouragement or additional support can be provided as needed. For example, a response could be, "I see you're having trouble finding the work instruction. We'll search for it right away, so please wait a moment."

[1309] As a concrete example, the following prompt sentence is shown.

[1310] Employee: "Show me the latest work order."

[1311] Robot: "Retrieving the latest work orders. Please wait."

[1312] (After database search)

[1313] Robot: "Here's the latest work order. I've put it on the screen."

[1314] As a concrete example of emotion analysis, the following exchange can be considered:

[1315] Employee: "I can't find the work order, what do I do?"

[1316] Robot: "I see you're having trouble finding your work order. I'll search for it right away, so please wait a moment."

[1317] (After database search)

[1318] Robot: "Here's your latest work order. I've put it up on the screen. Is there anything else I can help you with?"

[1319] In this way, employees not only get the information they need quickly and accurately, but also receive emotional support.

[1320] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1321] Step 1:

[1322] The user inputs questions or keywords to the robot by voice.

[1323] Input: User voice input

[1324] Output: Audio data

[1325] Specific behavior: The user says to the robot, "Show me the latest work instructions."

[1326] Step 2:

[1327] The robot's built-in microphone captures the voice and converts it into text using speech recognition software (e.g., Google Speech-to-Text API).

[1328] Input: Audio data

[1329] Output: Text data

[1330] Specific operation: The robot records the user's voice and converts the voice data into text.

[1331] Step 3:

[1332] The server uses a natural language processing engine (e.g., spaCy, BERT) to analyze the converted text and extract keywords and the intent of the question.

[1333] Input: Text data

[1334] Output: Extracted keywords and intent

[1335] Specific operation: The server extracts the keyword "latest work instructions" from the text "Show me the latest work instructions."

[1336] Step 4:

[1337] The server uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to analyze the emotional context of the text.

[1338] Input: Text data

[1339] Output: Emotion analysis results

[1340] What happens: The server detects frustration from the text "Work order not found."

[1341] Step 5:

[1342] The server searches the database for relevant documents and materials based on the extracted keywords.

[1343] Input: Extracted keywords

[1344] Output: Search results (related documents and materials)

[1345] Specific operation: The server searches the database using the keyword "latest work instructions" and retrieves relevant documents.

[1346] Step 6:

[1347] The server displays the search results on the display and notifies the user by voice.

[1348] Input: Search results

[1349] Output: Display and audio notification

[1350] Specific operation: The server will announce "This is the latest work instruction. It is displayed on the screen" and display the document on the screen.

[1351] Step 7:

[1352] The server then provides words of encouragement or additional support as needed based on the results of the sentiment analysis.

[1353] Input: Sentiment analysis results

[1354] Output: Additional support (e.g., words of encouragement)

[1355] Specific operation: The server will notify you by voice, "I see you're having trouble finding the work instructions. We'll search for them right away, so please wait a moment."

[1356] Example 2

[1357] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1358] It is difficult for employees to quickly and efficiently find the documents and materials they need. Information is provided without considering employees' emotional context, which can increase employee stress and frustration. Furthermore, there is a lack of ways to organize documents and materials based on employees' emotions, making information management cumbersome.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1360] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion analysis engine, and means for automatically storing the documents and materials in specific folders or directories based on the emotional context. This enables employees to find the information they need quickly and efficiently, and organizing information based on emotional context can reduce employee stress and frustration.

[1361] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1362] A "machine learning model" is an algorithm that learns patterns based on data and makes predictions and classifications.

[1363] An "emotion analysis engine" is software that analyzes the emotional context of text entered by employees.

[1364] A "folder or directory" is a digital repository for organizing and storing documents and materials.

[1365] "Search results" are the list of relevant documents and resources returned by the search engine based on the employee's question or keywords.

[1366] "Employee" means a user who uses the system to search and organize documents and materials.

[1367] "Documents and materials" are digital files containing information that employees need to perform their jobs.

[1368] "Emotional context" refers to the feelings and mental state that can be read from the text entered by an employee.

[1369] This invention is a system that enables employees to quickly and efficiently find documents and materials they need. The system is composed of a server that includes a natural language processing engine, a sentiment analysis engine, a search engine, and a database, and a terminal operated by a user.

[1370] The server receives search queries entered by employees on their devices and analyzes them using a natural language processing engine. The natural language processing engine incorporates machine learning models to understand the employee's questions and keywords and search for relevant documents and materials. The search engine uses common search software such as Apache Solr and Elasticsearch.

[1371] The search results are displayed in a list format in order of relevance. The server provides the search results to the user's terminal, and the user can select the documents or materials they need.

[1372] The server then uses a sentiment analysis engine to analyze the employee's emotional context. The sentiment analysis engine uses IBM Watson and Microsoft Azure sentiment analysis APIs. It recognizes emotions from phrases and search queries entered by employees and organizes documents and materials accordingly. For example, if an employee enters the phrase "I can't find the sales report," the sentiment analysis engine will recognize frustration and automatically store related documents and materials in a "Frustration" folder.

[1373] As a concrete example, consider the case where a user types "I'm looking for marketing materials for a new product." The device sends this query to the server. The server uses Elasticsearch to search for relevant marketing materials and generates results in order of relevance. At the same time, the server uses IBM Watson's sentiment analysis API to analyze the emotion of "anticipation." The server displays the search results in a list on the user's device and automatically stores related documents in an "anticipation" folder. The user can select the materials they need from the displayed list and view them.

[1374] Examples of prompts include:

[1375] "I'm looking for marketing materials for a new product."

[1376] I can't find the sales report

[1377] "I'm looking for a document that summarizes customer feedback."

[1378] In this way, the server can provide the information the user needs quickly and efficiently.

[1379] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1380] Step 1:

[1381] The user enters a search query.

[1382] The user enters the required information into the device's search bar, for example, "I'm looking for marketing materials for a new product." The entered search query becomes the input data for the next step.

[1383] Step 2:

[1384] The device sends a search query to the server.

[1385] The device sends the search query entered by the user to the server. This communication uses an HTTP request. The sent search query becomes the server's input data.

[1386] Step 3:

[1387] The server uses a search engine to generate search results.

[1388] The server passes the received search query to a search engine such as Apache Solr or Elasticsearch to search for relevant documents and materials. The search engine returns relevant results from its indexed database. The search results serve as input data for the next step.

[1389] Step 4:

[1390] The server analyzes the user's emotions using an emotion analysis engine.

[1391] The server uses IBM Watson or Microsoft Azure sentiment analysis APIs to analyze emotions from user search queries. For example, from a query like "I'm looking for marketing materials for a new product," it can recognize emotions such as "expectation" and "excitement." The analyzed emotions become input data for the next step.

[1392] Step 5:

[1393] The server displays the search results in a list format in order of relevance.

[1394] The server sorts the results returned by the search engine in order of relevance and displays them in a list format on the user's device. The user can then select the documents or materials they need from this list. The displayed search results become the input data for the next step.

[1395] Step 6:

[1396] The server organizes documents and materials based on emotions.

[1397] The server automatically stores related documents and materials in specific folders and directories based on the emotions analyzed by the emotion analysis engine. For example, if the emotion of "expectation" is recognized, related documents are stored in the "expectation" folder. The organized documents and materials become input data for the next step.

[1398] Step 7:

[1399] The user selects the documents and materials they need.

[1400] The user selects the documents or materials they need from the displayed list of search results. The selected documents or materials are either downloaded to the user's device or displayed in a viewable format. The selected documents or materials become the final output data.

[1401] (Application example 2)

[1402] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1403] When employees cannot quickly find the documents and materials they need, it can lead to reduced work efficiency and increased stress. Furthermore, the quality of work can decline if appropriate support is not provided based on the employee's emotional state. In particular, in workplaces such as factories, quick and accurate searches for work instructions and manuals are required, but current systems do not adequately achieve this.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1405] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion engine and organizing the documents and materials based on the analyzed results, and means for sorting relevant documents and materials according to the employee's emotions and providing detailed explanations and videos as needed. This allows employees to quickly find the information they need and provides appropriate support according to their emotional state, thereby improving work efficiency and reducing stress.

[1406] A "natural language processing engine" is a technology that analyzes employee questions and keywords and searches for related documents and materials.

[1407] "Search results" are a list of documents and materials searched by the natural language processing engine.

[1408] The "emotion engine" is a technology that analyzes employees' emotional context and organizes documents and materials based on that.

[1409] "Emotional context" is the emotional state inferred from the questions and keywords entered by the employee.

[1410] "Sorting" means arranging documents or materials based on specific criteria.

[1411] "Elaboration" means providing additional information or specific steps to a document or resource.

[1412] "Video" refers to video content that provides information visually.

[1413] A "folder" is a virtual storage location for organizing documents and materials.

[1414] A "directory" is a structure for organizing files and folders in a computer system.

[1415] A system for implementing this invention has the following configuration: The server includes a natural language processing engine, an emotion engine, a document search engine, and a database. The terminal includes a voice input device, a display, and an interface. A user accesses the system through the terminal and inputs questions or keywords.

[1416] The server first uses a natural language processing engine to analyze the question and keywords entered by the user. Based on this analysis, a document search engine searches the database for relevant documents and materials. The search results are sorted in order of relevance and provided to the user.

[1417] The emotion engine then analyzes the emotional context from the user's input. For example, if the user types, "I don't know how to install this part," the emotion engine recognizes the user's frustration. Based on this emotional context, the server further sorts relevant documents and resources, providing detailed instructions or videos as needed.

[1418] For example, consider a factory worker typing, "I don't know how to install this part." In this case, the server searches for relevant manuals, and if the emotion engine recognizes the worker's frustration, it provides detailed instructions and videos. This allows the worker to quickly obtain the information they need, improving work efficiency.

[1419] An example of a prompt to input to a generative AI model is as follows:

[1420] Create a program that analyzes the sentiment of employees when they type the phrase "I don't know how to install this part" and searches for and displays relevant documents and manuals. If employees are frustrated, provide detailed instructions or videos as well.

[1421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1422] Step 1:

[1423] The user inputs a question or keyword through the terminal.

[1424] Input: The user enters a question or keyword by voice or text.

[1425] Output: The device sends the entered question or keyword to the server.

[1426] Step 2:

[1427] The server uses a natural language processing engine to analyze the user's questions and keywords.

[1428] Input: Questions or keywords sent from the device.

[1429] Data processing: A natural language processing engine uses machine learning models to analyze the meaning of questions and keywords.

[1430] Output: Keywords and phrases as analysis results.

[1431] Step 3:

[1432] The server uses a document search engine to search a database for relevant documents and materials based on the analysis results.

[1433] Input: Analysis results of the natural language processing engine.

[1434] Data calculation: A document search engine searches through documents and materials in a database and lists them in order of relevance.

[1435] Output: A list of relevant documents and materials.

[1436] Step 4:

[1437] The server sends the search results to the terminal, which then provides them to the user.

[1438] Input: List of relevant documents and materials.

[1439] Output: The device displays the search results to the user.

[1440] Step 5:

[1441] The server uses an emotion engine to parse the emotional context from the user's input.

[1442] Input: User question or keywords.

[1443] Data processing: The emotion engine analyzes emotions from user input and identifies emotional context.

[1444] Output: Emotional context (e.g., frustration).

[1445] Step 6:

[1446] The server re-sorts relevant documents and materials based on emotional context, adding detailed descriptions and videos as needed.

[1447] Input: A list of documents and materials related to the emotional context.

[1448] Data operations: Re-sorting documents and materials based on emotional context, adding detailed descriptions and videos.

[1449] Output: A re-sorted list of documents and resources, plus additional explanations and videos.

[1450] Step 7:

[1451] The server sends the re-sorted list of documents and materials, along with additional explanations and videos, to the terminal, which then provides them to the user.

[1452] Input: A re-sorted list of documents and materials, plus additional explanations and videos.

[1453] Output: The device displays the re-sorted document or material to the user, along with any additional instructions or videos.

[1454] Example 3

[1455] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1456] Employees have difficulty quickly and efficiently searching and organizing the documents and materials they need. This can be especially true when employees are under emotional stress.

[1457] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for searching for related documents and materials based on the employee's question or keywords using a natural language processing engine, means for analyzing the emotional context of the employee's question or keywords using an emotion engine, means for providing the search results to the employee, and means for organizing the documents and materials based on the search results. This enables employees to quickly and efficiently search for the documents and materials they need and organize information while reducing emotional stress.

[1458] A "natural language processing engine" is software that analyzes employee questions and keywords, understands their meaning, and searches for related documents and materials.

[1459] An "emotion engine" is software that analyzes the emotional context contained in employees' questions and keywords and recognizes their emotional state.

[1460] "Searching means" is a function that uses a natural language processing engine to search a database for relevant documents and materials based on an employee's questions or keywords.

[1461] "Means of provision" refers to the function of displaying search results to employees and enabling them to access the necessary documents and materials.

[1462] "Organizing means" is a function that categorizes documents and materials based on search results and automatically stores them in folders or directories corresponding to each category.

[1463] A "machine learning model" is an algorithm that learns from data and is used by natural language processing engines to analyze questions and keywords.

[1464] "Categorization" is the process of classifying and organizing documents and materials based on specific criteria.

[1465] A "folder or directory" is a digital repository for storing documents or materials.

[1466] MODE FOR CARRYING OUT THE INVENTION

[1467] The present invention is a system for enabling employees to quickly and efficiently search for and organize documents and materials they need. A specific embodiment of this system will be described below.

[1468] System configuration

[1469] This system consists of three main components: a server, a terminal, and a user. The server is equipped with a natural language processing engine and an emotion engine, and is responsible for analyzing user input and searching and organizing related documents and materials. The terminal provides an interface for users to access the system and input questions and keywords.

[1470] Hardware and software used

[1471] Natural Language Processing Engine: Use natural language processing software such as the Google Cloud Natural Language API.

[1472] Sentiment engine: Uses sentiment analysis software such as IBM Watson Tone Analyzer.

[1473] Database: Use a database system to store documents and materials, such as a SQL database or a NoSQL database.

[1474] Data processing and calculation

[1475] The server receives questions and keywords entered by the user through their device. The received input is first analyzed by a natural language processing engine. This analysis allows the meaning of the entered keywords and question to be understood, and relevant documents and materials are searched for in a database. At the same time, an emotion engine analyzes the emotional context contained in the user's input and recognizes the user's emotional state.

[1476] Based on the analysis results, the server selects the most relevant documents and materials and categorizes them. Categorized documents and materials are automatically stored in folders or directories corresponding to their categories. For example, documents related to the "Sales Report" category are stored in the "Sales Report" folder.

[1477] Specific examples

[1478] If the user inputs "I can't find the latest sales report" into the terminal, the process will proceed as follows:

[1479] 1. The user types "I can't find the latest sales report" into the terminal.

[1480] 2. The device sends this input to the server via an HTTP request.

[1481] 3. The server uses the Google Cloud Natural Language API to analyze "latest sales report" as a keyword.

[1482] 4. The server uses IBM Watson Tone Analyzer to recognize the user's frustration from the phrase "not found."

[1483] 5. The server searches the database for documents related to "sales reports."

[1484] 6. The server automatically stores the search results in the "Sales Report" folder.

[1485] 7. The server generates a link to the organized document and sends it back to the device.

[1486] 8. The user clicks on the link sent back via the device to access the organized "Sales Report."

[1487] Prompt Sentence Examples

[1488] "I can't find my latest sales report. Please find relevant documents and organize them into a sales report folder."

[1489] This system allows users to quickly and efficiently search and organize the information they need. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1490] Step 1:

[1491] The user enters a question or keyword into the device, for example, "I can't find the latest sales report." The entered data is sent to the server through the device's interface.

[1492] Step 2:

[1493] The terminal sends the input to the server. Specifically, it sends the user's input data to the server using an HTTP request. The input data is text data including the user's question and keywords.

[1494] Step 3:

[1495] The server analyzes the input data using a natural language processing engine. The server uses natural language processing software such as Google Cloud Natural Language API to analyze the meaning of the input question and keywords. As a result of the analysis, related keywords and phrases are extracted.

[1496] Step 4:

[1497] The server uses an emotion engine to analyze the emotional context. The server uses emotion analysis software such as IBM Watson Tone Analyzer to analyze the emotional state contained in the user's input. For example, the server recognizes the user's frustration from the phrase "I can't find it." The analysis results in the output emotional state.

[1498] Step 5:

[1499] The server searches the database for related documents and materials. Based on the analysis results of the natural language processing engine and emotion engine, the server searches the database for related documents and materials. A list of related documents and materials is output as the search results.

[1500] Step 6:

[1501] The server categorizes the search results and stores them in the corresponding folders. The server categorizes the search results into specific categories and automatically stores them in folders or directories corresponding to each category. For example, documents related to the "Sales Report" category are stored in the "Sales Report" folder. A list of categorized documents and materials is output.

[1502] Step 7:

[1503] The server returns links to the organized documents and materials to the terminal. The server generates links to the categorized documents and materials and returns them to the terminal as an HTTP response. The returned links are output in a format that the user can access.

[1504] Step 8:

[1505] Users access organized documents and materials through their devices. Users click on links displayed on their devices to access organized documents and materials. This allows users to quickly and efficiently obtain the information they need.

[1506] (Application example 3)

[1507] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1508] The problem is that it is difficult for employees to efficiently search and organize large amounts of documents and materials. In addition, search results are provided without taking into account the emotional context of employees, which can make it difficult to quickly find the information they need. In particular, in environments such as logistics centers, where document and material management is cumbersome, efficient search and organization are required.

[1509] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1510] In this invention, the server includes means for using a natural language processing engine to search for relevant documents and materials based on employee questions and keywords, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the employee's emotional context using an emotion analysis engine to provide more relevant documents and materials, and means for categorizing the search results and automatically storing them in folders or directories corresponding to each category, thereby enabling employees to quickly and efficiently search for and organize the information they need.

[1511] A "natural language processing engine" is a technology that analyzes employee questions and keywords and searches for related documents and materials.

[1512] An "emotion analysis engine" is a technology that analyzes the emotional context based on employee input and provides more relevant documents and materials.

[1513] "Search results" refers to a collection of documents or materials searched by a natural language processing engine.

[1514] "Categorization" is the process of classifying search results into specific categories and automatically storing them in folders or directories corresponding to each category.

[1515] A "folder or directory" is a digital storage location for organizing and storing documents and materials.

[1516] "Employee" refers to a user who uses the system to search and organize documents and materials.

[1517] A "machine learning model" is an algorithm that learns from data and improves the performance of natural language processing engines and sentiment analysis engines.

[1518] "Documents and materials" is a general term for text and digital files containing information related to work.

[1519] The system for implementing the present invention includes a natural language processing engine, a sentiment analysis engine, and a function for categorizing search results and automatically storing them in folders. Specific embodiments are described below.

[1520] System Configuration

[1521] The server uses a natural language processing engine to search for relevant documents and materials based on the employee's questions and keywords. The sentiment analysis engine analyzes the emotional context based on the employee's input to provide more relevant documents and materials. Search results are categorized and automatically stored in folders and directories corresponding to each category.

[1522] Hardware and software used

[1523] Hardware: Smartphones, servers

[1524] Software: Python, Transformers library

[1525] Data processing and calculation

[1526] The server receives questions and keywords entered by employees using their smartphones. The natural language processing engine analyzes the entered text and searches the database for relevant documents and materials. The sentiment analysis engine analyzes the emotional context of the entered text to improve the relevance of search results. Search results are categorized and automatically stored in corresponding folders and directories.

[1527] Specific examples

[1528] If an employee uses their smartphone to type, "I can't find the latest sales report," the sentiment analysis engine will interpret their frustration. The natural language processing engine will search for documents related to "sales report," categorize them, and store them in folders. This allows employees to quickly and efficiently find and organize the information they need.

[1529] Prompt Sentence Examples

[1530] I can't find the latest sales report.

[1531] When this prompt is entered, the sentiment analysis engine analyzes the frustration, and the natural language processing engine searches for documents related to "sales reports," categorizes them, and stores them in folders.

[1532] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1533] Step 1:

[1534] A user enters a question or keyword using a smartphone.

[1535] Input: A question or keyword entered by the user (e.g., "I can't find the latest sales report")

[1536] Output: The input text data

[1537] Step 2:

[1538] The server receives the input text data and passes it to the natural language processing engine.

[1539] Input: Text data received from the user

[1540] Output: Text data passed to the natural language processing engine

[1541] Step 3:

[1542] A natural language processing engine analyzes the text data and searches the database for relevant documents and materials.

[1543] Input: Text data passed to the natural language processing engine

[1544] Output: List of relevant documents and materials

[1545] Step 4:

[1546] The server passes the text data to a sentiment analysis engine to analyze the emotional context.

[1547] Input: Text data passed to the natural language processing engine

[1548] Output: Sentiment analysis result (e.g., frustration)

[1549] Step 5:

[1550] Based on the results of the sentiment analysis engine, the server selects highly relevant documents and materials.

[1551] Input: Sentiment analysis results and a list of related documents and materials

[1552] Output: A list of relevant documents and resources

[1553] Step 6:

[1554] The server categorizes related documents and materials and automatically stores them in folders and directories corresponding to each category.

[1555] Input: A list of relevant documents and materials

[1556] Output: Folders or directories containing categorized documents and materials

[1557] Step 7:

[1558] The server provides the user with search results and notifies them of the folders in which relevant documents and materials are stored.

[1559] Input: Categorized document and resource information

[1560] Output: Search results and folder information provided to the user

[1561] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1562] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of a data generation model58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1563] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1564] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1565] [Third embodiment]

[1566] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1567] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1568] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1569] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1570] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1571] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1572] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1573] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1574] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1575] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1576] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1577] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1578] "Example 1"

[1579] In one embodiment of the present invention, the natural language processing engine analyzes employee questions and keywords based on machine learning models. Specifically, when an employee enters a keyword such as "latest sales report," the natural language processing engine analyzes the keyword and searches a database for related documents and materials.

[1580] "Example 2"

[1581] The search results are provided to employees. Specifically, the search results are displayed in a list format, allowing employees to select the documents and materials they need. The search results are also displayed in order of relevance, allowing employees to quickly find the information they need.

[1582] "Example 3"

[1583] Furthermore, documents and materials are organized based on the search results. Specifically, search results are categorized and automatically stored in folders or directories corresponding to each category. For example, if there is a category called "Sales Reports," documents and materials related to this category will be automatically stored in the "Sales Reports" folder. This allows employees to efficiently search for and organize the information they need.

[1584] The processing flow of each embodiment will be described below.

[1585] "Example 1"

[1586] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[1587] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[1588] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[1589] "Example 2"

[1590] Step 1: An employee enters a question or keyword into the system. For example, they enter a keyword such as "latest sales report."

[1591] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and resources. This analysis is based on machine learning models.

[1592] Step 3: The search results are displayed in a list format, allowing employees to select the documents or materials they need. The search results are also displayed in order of relevance.

[1593] Step 4: The selected documents and materials will be automatically stored in folders or directories corresponding to their categories. For example, if there is a category called "Sales Reports", documents and materials related to this category will be automatically stored in the "Sales Reports" folder.

[1594] Example 1

[1595] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1596] For employees to perform their work efficiently, it is important to be able to quickly search and retrieve the documents and materials they need. However, with conventional systems, keyword searches were inaccurate, and it often took a long time to find relevant documents and materials. In addition, the search results were manually organized, which was inefficient and prone to errors. To solve these issues, a system with more accurate search functions and automatic organization functions was needed.

[1597] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1598] In this invention, the server includes: means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine; means for providing the search results to the employee; means for organizing the documents and materials based on the search results; means for the employee to input keywords from a terminal; means for the terminal to transmit the input keywords to the server; means for the server to pass the keywords to the natural language processing engine; means for the natural language processing engine to analyze the keywords; means for the server to search a database based on the analysis results; means for the server to return search results to the terminal; and means for the terminal to display the search results to the employee. This allows employees to quickly and accurately search for and obtain the documents and materials they need. Furthermore, the automatic organization of search results improves work efficiency and reduces errors.

[1599] A "natural language processing engine" is software that uses machine learning models to analyze human language and understand its meaning.

[1600] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[1601] A "question" is an inquiry that an employee enters to obtain information.

[1602] "Keywords" are words or phrases that employees enter to search for specific information.

[1603] "Documents" are materials such as text files and reports that contain information related to business.

[1604] "Materials" are data and documents that contain information related to business.

[1605] A "searching means" is a method for identifying relevant documents or materials using a natural language processing engine.

[1606] The "means of providing" is the method for displaying the search results to employees.

[1607] "Organization methods" are methods for categorizing documents and materials based on search results and storing them in appropriate folders or directories.

[1608] "Terminals" are devices used by employees, such as computers and smartphones.

[1609] A "server" is a computer system that receives and processes requests from terminals.

[1610] A "database" is a collection of information in which documents and materials are stored.

[1611] "Means of analysis" refers to a method of using a natural language processing engine to understand the meaning of keywords and extract related information.

[1612] "Search Results" means a list of relevant documents or materials identified by a natural language processing engine.

[1613] "Display means" refers to a method for visually displaying search results on a terminal.

[1614] This invention is a system for quickly searching and retrieving documents and materials necessary for employees to perform their work efficiently. This system has the function of analyzing employee questions and keywords using a natural language processing engine and searching a database for related documents and materials.

[1615] Hardware and software used

[1616] Hardware

[1617] Server: A powerful computer system that manages databases and runs natural language processing engines.

[1618] Devices: These are devices used by employees, such as computers and smartphones.

[1619] software

[1620] Natural language processing engine: Uses machine learning models (e.g., BERT and GPT-3) to analyze employee questions and keywords.

[1621] Database: A collection of information in which documents and materials are stored, for example using MySQL.

[1622] Data processing and calculation

[1623] The server receives keywords entered by employees on their devices and sends them to a natural language processing engine. The natural language processing engine uses a machine learning model to analyze the keywords and extract information to identify related documents and materials. The server searches a database based on the analysis results and retrieves related documents and materials. The retrieved search results are returned from the server to the device and displayed for the employee to view.

[1624] Specific examples

[1625] As a concrete example, consider the case where an employee inputs the "latest sales report." In this case, the server performs the following process.

[1626] 1. The user types "Latest sales report" into the input field on the terminal.

[1627] 2. The device sends the keyword to the server using an HTTP POST request.

[1628] 3. The server passes the keywords to a natural language processing engine.

[1629] 4. The natural language processing engine uses the BERT model to parse the "latest sales report."

[1630] 5. The server uses the analysis results to search the MySQL database and identify the latest sales report.

[1631] 6. The server returns the search results to the device in JSON format.

[1632] 7. The terminal displays the search results to the user, allowing the user to view the latest sales report.

[1633] Prompt Sentence Examples

[1634] Below is an example of a prompt that the user might enter:

[1635] "View the latest sales report."

[1636] "Please tell me your sales data for 2023."

[1637] "Look for marketing materials for new products."

[1638] In this way, the user can easily obtain the information he or she needs.

[1639] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1640] Step 1:

[1641] The user inputs a keyword from the terminal.

[1642] Specifically, the user inputs a keyword such as "latest sales report" into an input field on the terminal, and the input keyword is temporarily stored in the terminal's memory.

[1643] Input: The keyword entered by the user (e.g., "latest sales report")

[1644] Output: Keywords saved on the device

[1645] Step 2:

[1646] The terminal sends the entered keyword to the server.

[1647] Specifically, the terminal uses an HTTP POST request to send the input keyword to the server, with the keyword included in the request body.

[1648] Input: Keywords saved on your device

[1649] Output: Keywords sent to the server

[1650] Step 3:

[1651] The server passes the keywords to a natural language processing engine.

[1652] Specifically, the server passes the received keywords to the natural language processing engine, where the keywords are passed as parameters in the API request.

[1653] Input: The keyword sent to the server

[1654] Output: Keywords passed to the natural language processing engine

[1655] Step 4:

[1656] A natural language processing engine analyzes keywords.

[1657] Specifically, natural language processing engines use machine learning models (e.g., BERT or GPT-3) to analyze keywords, generating information that can be used to identify related documents and resources.

[1658] Input: Keywords passed to the natural language processing engine

[1659] Output: Analysis results (information on related documents and materials)

[1660] Step 5:

[1661] The server searches the database based on the analysis results.

[1662] Specifically, the server searches a database (e.g., MySQL) based on the analysis results. A search query is generated based on the analysis results and executed against the database.

[1663] Input: Analysis results

[1664] Output: Search results (related documents and materials) retrieved from the database

[1665] Step 6:

[1666] The server returns the search results to the device.

[1667] Specifically, the server returns the search results obtained from the database to the terminal in JSON format, etc., as an HTTP response.

[1668] Input: Search results retrieved from the database

[1669] Output: Search results sent to your device

[1670] Step 7:

[1671] The terminal displays the search results to the user.

[1672] Specifically, the terminal displays the search results received from the server on the user interface, for example, displaying a link to the latest sales report and a preview of its contents.

[1673] Input: Search results sent to your device

[1674] Output: Search results (related documents and resources) displayed to the user

[1675] (Application example 1)

[1676] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1677] Logistics centers face the challenge of making it difficult for employees to quickly obtain the information they need. In particular, there is a lack of efficient ways to search for and provide information such as inventory status, delivery schedules, and the location of items in the warehouse. This can lead to reduced operational efficiency, delays, and errors.

[1678] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1679] In this invention, the server includes means for searching for related documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing questions entered by the employee via voice or text and searching for related information from a database, and means for displaying the search results on a smartphone, thereby enabling employees to quickly obtain the information they need and improving work efficiency.

[1680] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1681] A "machine learning model" is an algorithm that learns from data and analyzes questions and keywords.

[1682] A "database" is a collection of data structured to allow efficient searching and retrieval of related information.

[1683] A "smartphone" is a portable electronic device that analyzes questions entered via voice or text and displays search results.

[1684] "Search results" are relevant information retrieved from a database based on the question or keywords analyzed by the natural language processing engine.

[1685] "Documents and materials" are any collection of text or data that contains information employees need.

[1686] "Categorization" is the process of classifying documents and materials based on search results and automatically storing them in folders or directories corresponding to their categories.

[1687] "Questions entered via voice or text" are inquiries entered by employees via their smartphones in voice or text format.

[1688] "Related information" refers to the necessary data and materials searched from the database in response to an employee's question or keyword.

[1689] A system for implementing this invention includes a natural language processing engine, a machine learning model, a database, and a smartphone. The specific configuration and operation of the system will be described below.

[1690] System configuration

[1691] 1. Natural language processing engine: Software that analyzes questions and keywords entered by employees and searches for relevant documents and materials. Specifically, it uses a natural language processing library such as spaCy.

[1692] 2. Machine learning model: An algorithm used to analyze questions and keywords. It is built using a machine learning library such as scikit-learn.

[1693] 3. Database: A structured collection of data for efficient searching and retrieval of related information. Use a database management system such as SQLite.

[1694] 4. Smartphone: A handheld electronic device that allows employees to enter questions by voice or text and display search results. iOS or Android smartphones are used.

[1695] System Operation

[1696] 1. User input: An employee uses a smartphone to input a question in voice or text format. For example, they input a prompt such as "Please tell me the latest inventory status."

[1697] 2. Natural Language Processing: The server uses a natural language processing engine to analyze the user's input and extract keywords, such as "stock status" and "latest."

[1698] 3. Database search: The server searches the database based on the extracted keywords to retrieve relevant documents and materials, for example, documents containing the latest inventory information.

[1699] 4. Providing search results: The server sends the search results to the smartphone and displays them to the user, allowing employees to quickly obtain the information they need.

[1700] Specific examples

[1701] When an employee types "Please tell me the latest inventory status" into their smartphone, the natural language processing engine extracts keywords such as "inventory status" and "latest" and searches the database for the latest inventory information. As a result, the latest inventory information is displayed on the smartphone.

[1702] Other example prompts might include questions such as "What is the latest delivery schedule?" or "Where are the items located in the warehouse?"

[1703] This system allows employees to quickly obtain the information they need, improving work efficiency.

[1704] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1705] Step 1:

[1706] The user inputs a question in voice or text format using a smartphone.

[1707] Input: A user's voice or text question (e.g., "What is the latest inventory status?")

[1708] Output: Question data entered into a smartphone

[1709] How it works: A user launches an application on their smartphone and uses voice or text input. In the case of voice input, the speech recognition software converts the speech into text.

[1710] Step 2:

[1711] The server uses a natural language processing engine to analyze the user's input and extract keywords.

[1712] Input: User's question data (text format)

[1713] Output: Extracted keywords (e.g., "Availability", "Latest")

[1714] How it works: The server uses a natural language processing library such as spaCy to analyze the text and extract important keywords, for example, by performing morphological analysis to identify important words such as nouns and verbs.

[1715] Step 3:

[1716] The server searches the database based on the extracted keywords to retrieve related documents and materials.

[1717] Input: Extracted keywords (e.g., "inventory status," "latest")

[1718] Output: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[1719] Specific operation: The server uses a database management system such as SQLite to search for documents or materials that match the keywords, for example, by executing an SQL query to retrieve records that match the keywords.

[1720] Step 4:

[1721] The server sends the search results to the smartphone and displays them to the user.

[1722] Input: Relevant documents and materials (e.g., documents containing up-to-date inventory information)

[1723] Output: Search results displayed on a smartphone

[1724] Specific operation: The server converts the search results into a data format such as JSON and sends it to the smartphone. The smartphone application analyzes the received data and displays it in a format that is easy for the user to view.

[1725] Step 5:

[1726] The user checks the search results displayed on the smartphone and obtains the information they need.

[1727] Input: Search results displayed on smartphone

[1728] Output: The information the user needs (e.g., the latest inventory information)

[1729] Specific operation: The user checks the search results displayed on the smartphone screen and obtains the necessary information, such as stock availability and delivery schedules.

[1730] Example 2

[1731] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1732] Employees need to be able to search for the documents and materials they need quickly and efficiently, and to receive results organized in order of relevance. However, with conventional systems, search results were not properly organized, making it time-consuming to find the information they needed. Furthermore, the display format of search results was inappropriate, making it difficult for users to quickly find the information they needed.

[1733] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1734] In this invention, the server includes means for searching for documents and materials related to employee questions and keywords using a natural language processing engine, means for sorting the search results in descending order of relevance, and means for generating a list of the search results, thereby enabling employees to quickly and efficiently find the information they need.

[1735] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1736] "Searching tools" is the ability to find documents and materials in the database based on employee questions or keywords.

[1737] The "means of providing" is the function for displaying search results to employees.

[1738] "Sorting means" is a function for organizing search results in order of relevance.

[1739] The "means for generating" is a function for formatting search results in a list format.

[1740] The "display means" is a function for displaying the generated search results on the employee's terminal.

[1741] A "machine learning model" is an algorithm that analyzes questions and keywords based on data.

[1742] "Categorization means" is a function that categorizes search results based on specific criteria and automatically stores them in folders or directories corresponding to each category.

[1743] MODE FOR CARRYING OUT THE INVENTION

[1744] The present invention is a system that enables employees to quickly and efficiently search for documents and materials they need, and provides results organized in order of relevance. Specific embodiments of this system are described below.

[1745] System configuration

[1746] The system consists of three main components: a server, a terminal, and a user. The server uses a natural language processing engine and machine learning models to analyze search queries and retrieve relevant documents and materials. The terminal is a device where users input search queries and display search results. The user is an employee who uses the system to search for the information they need.

[1747] Hardware and software used

[1748] Server: Use a computer system with a high-performance processor and large memory capacity. On the server, install a Python-based library (e.g., NLTK, spaCy) as a natural language processing engine, and use Elasticsearch as the search algorithm.

[1749] Terminal: A device used by a user, such as a PC or smartphone, on which a web browser and dedicated applications are installed.

[1750] Software: We use machine learning models (e.g., BERT, GPT) to analyze search queries, which allows us to analyze user questions and keywords with high accuracy.

[1751] System Operation

[1752] 1. User enters a search query

[1753] The user enters the required information into the device's search bar, for example, "project report."

[1754] 2. The device sends the search query to the server

[1755] The device sends the search query entered by the user to the server using an HTTP request.

[1756] 3. The server receives the search query and queries Elasticsearch

[1757] The server analyzes the search query received from the terminal and sends a search request to Elasticsearch.

[1758] 4. The server receives the search results from Elasticsearch

[1759] The server receives search results returned from Elasticsearch, which contain relevant document and resource information.

[1760] 5. The server sorts the search results by relevance.

[1761] The server sorts the received search results in order of relevance, using Elasticsearch's scoring function to evaluate relevance.

[1762] 6. The server generates a list of search results

[1763] The server formats the sorted search results into a list in HTML format.

[1764] 7. The server sends the search results to the device.

[1765] The server sends the generated search results in HTML format to the terminal using an HTTP response.

[1766] 8. The device displays the search results to the user.

[1767] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format.

[1768] 9. The user selects the documents and materials they need.

[1769] Users can select the documents or materials they need from the displayed search results, and click on the selected document to display details.

[1770] Specific examples

[1771] As a concrete example, consider the case where a user searches for "project report." The user enters "project report" into the terminal and clicks the search button. The server receives this query and uses Elasticsearch to search for documents in the database. The search results are sorted in order of relevance and displayed to the user in a list format. The user can then select the document they need from this list.

[1772] Prompt Sentence Examples

[1773] An example of a prompt sentence might be:

[1774] Prompt: "Find project reports"

[1775] When this prompt is input into the generative AI model, the AI ​​model will provide search results to help employees quickly find the project report they need.

[1776] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1777] Step 1:

[1778] The user enters a search query.

[1779] The user enters the required information into the device's search bar, for example, "project report," and the query is temporarily stored in the device's memory.

[1780] Step 2:

[1781] The device sends a search query to the server.

[1782] The device sends the search query entered by the user to the server as an HTTP request. This request includes the query entered by the user. After sending the request, the device waits for a response from the server.

[1783] Step 3:

[1784] The server receives the search query and queries Elasticsearch.

[1785] The server analyzes the search query received from the device and sends a search request to Elasticsearch. Specifically, the server passes the search query to Elasticsearch's API, instructing it to search for related documents and materials. The input is the search query, and the output is the search results from Elasticsearch.

[1786] Step 4:

[1787] The server receives the search results from Elasticsearch.

[1788] The server receives the search results returned from Elasticsearch. The search results contain information about related documents and resources. The server stores the results in memory for further processing. The input is the search results from Elasticsearch, and the output is the search results stored in the server's memory.

[1789] Step 5:

[1790] The server sorts the search results by relevance.

[1791] The server uses Elasticsearch's scoring function to sort the received search results in order of relevance. Specifically, it calculates the relevance score of each document and sorts them in order of highest to lowest. The input is the search results stored in the server's memory, and the output is the sorted search results.

[1792] Step 6:

[1793] The server generates the search results in a list format.

[1794] The server formats the sorted search results into a list in HTML format. Specifically, it wraps the title and summary of each document in HTML tags to make it easier for users to view. The input is the sorted search results, and the output is the HTML-formatted search results.

[1795] Step 7:

[1796] The search results generated by the server are sent to the terminal.

[1797] The server generates the search results in HTML format and sends them to the terminal as an HTTP response. The input is the search results in HTML format, and the output is the search results sent to the terminal.

[1798] Step 8:

[1799] The terminal displays the search results to the user.

[1800] The terminal displays the received HTML in a web browser and shows the search results to the user in a list format. Specifically, the web browser parses the HTML and displays it on the screen. The input is the HTML search results received from the server, and the output is the search results displayed to the user.

[1801] Step 9:

[1802] The user selects the documents and materials they need.

[1803] The user selects the necessary documents or materials from the displayed search results. Clicking on the selected document displays details. The input is the user's click operation, and the output is a detailed display of the selected document.

[1804] (Application example 2)

[1805] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1806] At logistics centers, employees are required to quickly search for necessary inventory and delivery information and carry out their work efficiently. However, with conventional systems, searching for information takes time and displays a lot of irrelevant information, resulting in reduced work efficiency. Furthermore, information search using smartphones is not fully utilized, making it difficult to respond quickly on-site.

[1807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1808] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for displaying inventory information and delivery information in order of relevance, and means for employees to quickly search for necessary information using their smartphones, thereby enabling employees to quickly search for necessary information and improving work efficiency.

[1809] A "natural language processing engine" is software that analyzes employee questions and keywords and searches for related documents and materials.

[1810] "Means for providing search results" refers to a function for displaying searched documents and materials to employees.

[1811] "Means for organizing documents and materials" refers to a function that categorizes documents and materials based on search results and automatically stores them in folders or directories corresponding to each category.

[1812] "A means for displaying inventory information and delivery information in order of relevance" is a function for sorting and displaying inventory data and delivery data in order of relevance based on a search query.

[1813] "Means for employees to quickly search for the information they need using their smartphones" refers to a function that allows employees to quickly search for the information they need using their smartphones.

[1814] A system for carrying out the present invention enables employees at a logistics center to quickly search for necessary inventory information and delivery information. A specific embodiment of this system will be described below.

[1815] System configuration

[1816] The system consists of the following main components:

[1817] 1. Server: Equipped with a natural language processing engine and machine learning models, it analyzes employee questions and keywords.

[1818] 2. Smartphone: Enter a search query on the employee's device and view the search results.

[1819] 3. Database: Stores inventory and shipping information.

[1820] Program processing

[1821] The server works as follows:

[1822] 1. Natural language processing engine: Analyzes questions and keywords entered by employees on their smartphones and searches for relevant documents and materials.

[1823] 2. Machine learning models: Generate search results in order of relevance based on an analysis of the question and keywords.

[1824] 3. Providing search results: Search results are sent to employees' smartphones and provided to them.

[1825] 4. Data organization: Documents and materials are categorized based on search results and automatically stored in folders and directories corresponding to each category.

[1826] 5. Display inventory and shipping information: Display inventory and shipping data sorted by relevance.

[1827] Hardware and software used

[1828] Hardware: Smartphones, servers

[1829] Software: Python, Pandas, Scikit-learn, natural language processing engine (e.g., SpaCy)

[1830] Specific examples

[1831] When an employee searches for "out of stock items," the system works as follows:

[1832] 1. An employee types "out of stock item" into their smartphone.

[1833] 2. The server's natural language processing engine parses the query and searches for relevant inventory information.

[1834] 3. The machine learning model generates search results in order of relevance.

[1835] 4. Search results are displayed on a smartphone, allowing employees to see a list of items that are out of stock.

[1836] Prompt Sentence Examples

[1837] Search query: "out of stock items"

[1838] In this way, logistics center employees can quickly find the information they need and improve work efficiency.

[1839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1840] Step 1:

[1841] A user types a search query into their smartphone.

[1842] Input: A user types "item out of stock" into their smartphone.

[1843] Output: The search query is sent to the server.

[1844] Specific operation: The user enters "out of stock items" into the search bar on their smartphone and presses the search button.

[1845] Step 2:

[1846] The server analyzes the search query using a natural language processing engine.

[1847] Input: A search query sent from a smartphone: "Products out of stock."

[1848] Output: Parsed query data.

[1849] What it does: The server's natural language processing engine (e.g., SpaCy) tokenizes the search query and extracts key keywords.

[1850] Step 3:

[1851] The server uses machine learning models to search for relevant documents and materials.

[1852] Input: Parsed query data.

[1853] Output: A list of relevant documents and materials.

[1854] What it does: The server's machine learning model (e.g., Scikit-learn) uses the parsed query data to search for inventory and delivery information in the database and sort it by relevance.

[1855] Step 4:

[1856] The server sends the search results to the smartphone.

[1857] Input: List of relevant documents and materials.

[1858] Output: Search results displayed on a smartphone.

[1859] Specific operation: The server sends a list of relevant documents and materials to the smartphone and displays it to the user.

[1860] Step 5:

[1861] The user checks the search results on their smartphone.

[1862] Input: Search results displayed on a smartphone.

[1863] Output: The user confirms the required information.

[1864] Specific behavior: The user scrolls through the search results displayed on their smartphone screen and checks the necessary inventory and delivery information.

[1865] Step 6:

[1866] The server organizes documents and materials based on the search results.

[1867] Input: List of relevant documents and materials.

[1868] Output: Categorized documents and materials.

[1869] Specific operation: The server categorizes documents and materials based on the search results and automatically stores them in folders or directories corresponding to each category.

[1870] Step 7:

[1871] The server displays inventory and delivery information in order of relevance.

[1872] Input: Relevant inventory and shipping information.

[1873] Output: Stock and shipping information sorted by relevance.

[1874] Specific behavior: The server sorts inventory and shipping data in order of relevance and displays it to the user.

[1875] Example 3

[1876] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1877] There is a problem that it is difficult for employees to efficiently search and organize the information they need. Especially when there are a large number of documents and materials, manual searching and organization takes time and effort, reducing work efficiency. In addition, if search results are not properly categorized, it is difficult to quickly find the information you need.

[1878] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes means for searching for relevant information based on the employee's question or keyword using a natural language processing engine, means for providing the employee with the search results, means for analyzing and categorizing information based on the search results, and means for automatically storing the categorized information in folders or directories corresponding to each category. This enables employees to efficiently search for and organize the information they need.

[1879] A "natural language processing engine" is software that analyzes natural language and understands its meaning.

[1880] An "employee" is an individual who belongs to a company or organization and performs work for that company or organization.

[1881] "Questions and keywords" are input data that employees use to search for information.

[1882] "Relevant information" refers to documents and materials retrieved based on an employee's question or keywords.

[1883] "Search methods" are methods and techniques for obtaining relevant information based on employee questions or keywords.

[1884] "Means of providing" refers to the methods and technologies used to display search results to employees.

[1885] "Means for analyzing and categorizing" refers to the methods and techniques used to analyze and categorize search results into specific categories.

[1886] "Folders and directories" are virtual storage locations for organizing information within a computer.

[1887] "Automatic storage means" refers to methods or techniques for automatically moving analyzed information into corresponding folders or directories.

[1888] A "machine learning model" is an algorithm that learns from data and makes predictions and classifications.

[1889] The present invention is a system for enabling employees to efficiently search for and organize necessary information. A specific embodiment of this system will be described below.

[1890] System configuration

[1891] This system consists of three main components: a server, a terminal, and a user.

[1892] 1. Server:

[1893] The server uses a natural language processing engine to search for relevant information based on employee questions and keywords. Specifically, it uses search engines such as Apache Solr and Elasticsearch. It also uses natural language processing tools such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding to analyze and categorize the search results. It then uses the Python os and shutil modules to automatically store the categorized information in the corresponding folders and directories.

[1894] 2. Terminal:

[1895] A terminal is a device on which a user inputs a search query and checks search results. Terminals include computing devices such as PCs, tablets, and smartphones.

[1896] 3. User:

[1897] Users are employees who use the system to search and organize information. Users use terminals to enter search queries and view organized information.

[1898] System Operation

[1899] 1. User enters a search query:

[1900] Users enter a question or keyword into the device's search bar, for example, "Sales report 2023."

[1901] 2. Server retrieves search results:

[1902] The server receives the search query entered by the user and retrieves relevant information from the database using Apache Solr or Elasticsearch.

[1903] 3. Server analysis and categorization of search results:

[1904] The server analyzes the search results using Google Cloud Natural Language API or IBM Watson Natural Language Understanding and categorizes them into appropriate categories, such as "sales reports," "financial reports," and "market analysis."

[1905] 4. Server stores files in folders by category:

[1906] The server automatically stores the categorized information in folders or directories corresponding to each category using the Python os and shutil modules. For example, information categorized as "Sales Report" is stored in the "Sales Report" folder.

[1907] 5. User review of organized information:

[1908] The user can use the device to view the organized folders, for example, by opening the "Sales Report" folder and viewing the information they need.

[1909] Examples of specific examples and prompts

[1910] Examples:

[1911] When a user searches for "Sales Report 2023", the specific operations are as follows:

[1912] 1. User: Enter "Sales Report 2023" into the device's search bar and click the search button.

[1913] 2. Server: Receives search queries and retrieves relevant information from the database using Apache Solr.

[1914] 3. Server: Analyze the acquired information using the Google Cloud Natural Language API and classify it into the "Sales Report" category.

[1915] 4. Server: Use Python's os module to move the classified information to the "Sales Report" folder.

[1916] 5. User: Open the "Sales Report" folder on the device and check the required information.

[1917] Example prompt sentence:

[1918] "Search for sales reports for 2023 and automatically store the relevant information in the sales reports folder."

[1919] This system allows users to efficiently search and organize the information they need. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1920] Step 1: User enters a search query

[1921] A user enters a question or keyword into the device's search bar. For example, they might enter "Sales Report 2023." The input data is text about the information the user wants to search for. The output is sent to the server as a search query.

[1922] Step 2: Server retrieves search results

[1923] The server receives a search query entered by a user and retrieves relevant information from a database using a search engine (e.g., Apache Solr or Elasticsearch). The input data is the user's search query. The server sends the search query to the search engine to retrieve relevant documents and materials. The output is a list of documents and materials as search results.

[1924] Step 3: Server analyzes and categorizes search results

[1925] The server analyzes the search results using a natural language processing engine (for example, Google Cloud Natural Language API or IBM Watson Natural Language Understanding). The input data are the documents and materials obtained as search results. The server analyzes these documents and classifies them into appropriate categories. For example, they could be categorized as "sales reports," "financial reports," or "market analysis." The output is a list of categorized documents and materials.

[1926] Step 4: The server stores the categories in folders

[1927] The server automatically stores categorized documents and materials in folders and directories corresponding to each category. The input data are categorized documents and materials. The server uses Python's os module and shutil module to obtain the document path and move it to the corresponding folder. For example, documents categorized in the "Sales Report" category are stored in the "Sales Report" folder. The output is the documents and materials stored in the folder.

[1928] Step 5: User reviews the organized information

[1929] The user uses a terminal to check the organized folders. The input data are the documents and materials stored in the folders. The user can open, for example, the "Sales Report" folder and view the necessary documents. The output is the documents and materials that the user views.

[1930] This system allows users to efficiently search and organize the information they need.

[1931] (Application example 3)

[1932] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1933] In conventional document management systems, searching and organizing documents and materials is often done manually, resulting in inefficiencies. Furthermore, many paper-based documents are used at logistics centers and other on-site locations, creating a need for a way to digitize and efficiently manage them. Furthermore, categorizing documents and uploading them to cloud storage is often done manually, which is time-consuming and labor-intensive.

[1934] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1935] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for extracting text from images using optical character recognition technology, means for categorizing the documents based on the extracted text and automatically storing them in corresponding folders, and means for uploading the documents to cloud storage, thereby enabling efficient search, organization, digitization, and automatic uploading of documents and materials to cloud storage.

[1936] A "natural language processing engine" is software that analyzes natural language and searches for relevant information based on questions or keywords.

[1937] "Employee" refers to a person who belongs to a company or organization and performs work.

[1938] "Search methods" refer to methods and techniques for finding specific information.

[1939] "Means of delivery" refers to the methods and technologies used to display or make accessible search results to users.

[1940] "Organizational methods" refer to methods and techniques for classifying and managing documents and materials based on specific criteria.

[1941] "Optical character recognition technology" is a technology for extracting character information from images.

[1942] "Image" refers to a digital file containing visual information.

[1943] "Text" refers to digital data containing textual information.

[1944] "Categorization" refers to classifying information based on specific criteria.

[1945] A "folder" refers to a virtual container for organizing digital data.

[1946] "Cloud storage" refers to a remote server for storing data over the Internet.

[1947] "Upload" refers to the transfer of data from a local device to a remote server.

[1948] A system for implementing this invention is configured as follows: First, the server uses a natural language processing engine to search for relevant documents and materials based on the employee's question and keywords. The natural language processing engine analyzes the question and keywords based on a machine learning model. The analyzed results are provided to the employee.

[1949] The server then organizes the documents and materials based on the search results. To organize them, it uses optical character recognition (OCR) technology to extract text from images. The extracted text is then categorized based on specific keywords and automatically stored in corresponding folders. The documents are then uploaded to cloud storage.

[1950] To realize this system, the following hardware and software are used: A smartphone with a camera is required for the hardware, and Python, an OCR library, PIL (Python Imaging Library), and Google Cloud Storage are used for the software.

[1951] As a concrete example, consider a document organization app used in a logistics center. When an employee takes a photo of a shipping instruction sheet with their smartphone camera, the image is converted into text using OCR technology. The converted text is classified into a category called "Shipping Instructions" and automatically stored in the corresponding folder. The document is then uploaded to cloud storage.

[1952] An example of a prompt sentence might be:

[1953] "Please develop a document organization app to be used in a logistics center. This application will analyze document images taken with a smartphone camera using OCR technology, automatically classify them into categories such as shipping instructions, receipts, and inventory lists, and upload them to cloud storage."

[1954] In this way, documents and materials can be efficiently searched, organized, digitized and automatically uploaded to cloud storage.

[1955] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1956] Step 1:

[1957] The user takes a photo of the document using the smartphone camera.

[1958] Input: Paper-based document

[1959] Output: Digital image file

[1960] Specific operation: The user launches the smartphone's camera app and takes a photo of a document. The captured image is saved in the smartphone.

[1961] Step 2:

[1962] The device uses optical character recognition (OCR) technology to extract text from the image.

[1963] Input: Digital image file

[1964] Output: Extracted text data

[1965] Specific operation: The device inputs the saved image file into OCR software and extracts the text information in the image as text data.

[1966] Step 3:

[1967] The device analyzes the extracted text and categorizes it.

[1968] Input: Extracted text data

[1969] Output: Category information

[1970] Specific operation: The terminal analyzes the extracted text data and determines categories based on specific keywords (e.g., "shipping instructions," "receipt," etc.).

[1971] Step 4:

[1972] The terminal automatically stores the documents in the corresponding folders based on the categories.

[1973] Input: Category information, digital image files

[1974] Output: Documents stored in a folder

[1975] Specific operation: The terminal moves or copies the digital image files to the corresponding folders based on the determined categories.

[1976] Step 5:

[1977] The device uploads the document to cloud storage.

[1978] Input: Documents stored in a folder

[1979] Output: Documents saved in cloud storage

[1980] Specific operation: The device uploads the documents in the folder to a cloud storage service (Google Cloud Storage). Once the upload is complete, the documents are stored in the cloud.

[1981] Step 6:

[1982] The server uses a natural language processing engine to search for relevant documents and materials based on the employee's questions and keywords.

[1983] Input: Employee question or keyword

[1984] Output: Search results for related documents and resources

[1985] Specific operation: The server inputs the questions and keywords entered by the employee into a natural language processing engine to search for relevant documents and materials, and provides the search results to the employee.

[1986] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1987] "Example 1"

[1988] In one embodiment of the present invention, a natural language processing engine and an emotion engine are combined.

[1989] When an employee enters a question or keyword into the system, the natural language processing engine analyzes the keyword and searches the database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question or keyword. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine will recognize the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[1990] "Example 2"

[1991] In another embodiment of the present invention, an emotion engine organizes documents and materials based on the employee's emotional context. Specifically, the emotion engine analyzes the employee's emotional context and automatically stores documents and materials in folders or directories corresponding to the respective emotional context. For example, if an employee types the phrase "I can't find the sales report," the emotion engine recognizes the employee's frustration from this phrase, and the system automatically stores the relevant documents and materials in a "Frustration" folder.

[1992] "Example 3"

[1993] In one embodiment of the present invention, a natural language processing engine and an emotion engine are combined.

[1994] When an employee enters a question or keyword into the system, the natural language processing engine analyzes the keyword and searches the database for relevant documents and materials. At the same time, the emotion engine analyzes the emotional context of the employee's question or keyword. For example, if an employee enters the phrase "I can't find the latest sales report," the emotion engine will recognize the employee's frustration from this phrase. This information is used by the system to provide more relevant documents and materials.

[1995] The processing flow of each embodiment will be described below.

[1996] "Example 1"

[1997] Step 1: An employee enters a question or keyword into the system.

[1998] Step 2: A natural language processing engine analyzes the keywords and searches the database for relevant documents and materials.

[1999] Step 3: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[2000] Step 4: The natural language processing engine uses the results of the emotion engine's analysis to provide more relevant documents and materials.

[2001] "Example 2"

[2002] Step 1: An employee enters a question or keyword into the system.

[2003] Step 2: The sentiment engine analyzes the emotional context of the employee's question and keywords.

[2004] Step 3: Based on the analysis results of the emotion engine, documents and materials are automatically stored in folders and directories that correspond to their emotional context.

[2005] Example 1

[2006] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[2007] Conventional systems were unable to consider emotional context when searching for documents and materials related to questions or keywords entered by employees, making it difficult to fully meet employees' needs. Furthermore, the organization and provision of search results did not provide appropriate information that reflected employees' emotions, hindering efficient work execution.

[2008] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2009] In this invention, the server includes means for searching for relevant documents and materials based on employee questions and keywords using a natural language processing engine, means for providing the search results to the employee, means for organizing the documents and materials based on the search results, means for analyzing the emotional context of the employee questions and keywords using an emotion engine, and means for providing highly relevant documents and materials based on the emotional context. This makes it possible to provide appropriate information that takes employee emotions into consideration, thereby improving work efficiency and employee satisfaction.

[2010] A "natural language processing engine" is software that analyzes questions and keywords entered by employees, understands their meaning, and searches for related documents and materials.

[2011] A "machine learning model" is an algorithm that learns from data and finds patterns and rules, and is used to improve the analytical capabilities of natural language processing engines.

[2012] The "emotion engine" is software that analyzes the emotional context contained in employees' questions and keywords and recognizes those emotions.

[2013] "Documents and materials" is a general term for texts, reports, presentations, data sheets, etc. that contain information employees need to perform their jobs.

[2014] A "database" is an information system for efficiently storing, searching, and managing documents and materials.

[2015] "Search Results" are a list of documents or materials retrieved from a database based on a question or keywords analyzed by a natural language processing engine and sentiment engine.

[2016] "Categorization" is the process of classifying documents or materials based on search results according to specific themes or attributes.

[2017] A "folder or directory" is a virtual storage location on a computer for organizing and storing documents and materials.

[2018] An "employee" is a user who uses the system to input questions or keywords to carry out work.

[2019] MODE FOR CARRYING OUT THE INVENTION

[2020] This invention is a system that analyzes questions and keywords entered by employees and provides relevant documents and materials. The system combines a natural language processing engine and an emotion engine to provide information that takes into account the employee's emotional context.

[2021] Hardware and software used

[2022] server

[2023] The server performs the main processing of the system using the following software:

[2024] Natural language processing engines (e.g., BERT, GPT-3)

[2025] Emotion engine (e.g., emotion analysis API)

[2026] Database management systems (e.g., MySQL, PostgreSQL)

[2027] Terminal

[2028] The terminal provides an interface for employees to enter questions or keywords. The terminal uses the following software:

[2029] Web browser or dedicated application

[2030] HTTP client library

[2031] User

[2032] The user (employee) enters a question or keyword into the system and checks the search results.

[2033] Data processing and calculation

[2034] Natural Language Processing Engine

[2035] The server passes the questions and keywords entered by employees to a natural language processing engine for analysis. The natural language processing engine uses machine learning models (e.g., BERT, GPT-3) to understand the meaning of the input text and extract keywords to search for related documents and materials.

[2036] Emotion Engine

[2037] The server passes the input text to an emotion engine that analyzes the emotional context. The emotion engine recognizes the employee's emotions (e.g., frustration, joy) from the input text and uses that information to provide relevant documents and resources.

[2038] Database search

[2039] The server uses the results of the natural language processing and emotion engines to search for relevant documents and materials from the database, and the search results are prioritized taking into account the employee's emotional context.

[2040] Providing and organizing results

[2041] The server sends the search results to the terminal, which displays them to the user. Furthermore, the terminal categorizes the documents and materials based on the search results and automatically stores them in folders and directories corresponding to each category.

[2042] Specific examples

[2043] If an employee types "I can't find the latest sales report," the device sends this input to the server. The server uses a natural language processing engine to analyze the keyword "latest sales report" and an emotion engine to recognize the employee's frustration from the phrase "I can't find it." The server uses this information to search for relevant documents in the database and sends the search results to the device. The device then displays the search results to the user.

[2044] Prompt Sentence Examples

[2045] "If an employee types into the system, 'I can't find the latest sales report,' how would the system respond?"

[2046] By feeding this prompt into a generative AI model, a response is obtained that details the system's behavior.

[2047] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2048] Step 1:

[2049] The user enters a question or keyword.

[2050] The user enters a question or keyword, such as "I can't find the latest sales report," into the system interface. The entered text is displayed in the input field on the device. Specific actions include the user entering text using the keyboard and clicking the send button.

[2051] Step 2:

[2052] The device sends input to the server.

[2053] The terminal sends the text entered by the user to the server. The input text is sent to the server as an HTTP request. Specifically, the terminal application generates an HTTP request and sends it to the server.

[2054] Step 3:

[2055] The server analyzes the input using a natural language processing engine.

[2056] The server passes the received text to a natural language processing engine for analysis. By analyzing the input text, related keywords and phrases are extracted. Specifically, the server calls the API of the natural language processing engine to obtain the analysis results. The input is the user's text, and the output is the analyzed keywords and phrases.

[2057] Step 4:

[2058] The server analyzes the emotional context with an emotion engine.

[2059] The server passes the input text to the emotion engine and analyzes the emotional context. The emotion engine recognizes the employee's emotion (e.g., frustration) from the input text. Specifically, the server calls the emotion engine's API to obtain the emotion analysis results. The input is the user's text, and the output is the analyzed emotional information.

[2060] Step 5:

[2061] The server searches the database for relevant documents and materials.

[2062] The server searches the...

Claims

1. A means for searching document data related to user input information using a natural language processing engine; means for analyzing the user's emotional context using an emotion engine; means for sorting the document data search results according to the emotional context of the user; means for providing the sorted search results to the user; A system including:

2. means for categorizing the document data based on the search results and automatically storing the document data in a storage location corresponding to each category; The system of claim 1 .

3. means for providing detailed explanations or videos according to the emotional context of the user; The system of claim 1 .

Images