system

Abstract

We provide the system. [Solution] A means for receiving questions entered in natural language, A natural language processing means for analyzing the question and extracting necessary information, A query generation means that queries the database based on the extracted information, A data analysis method for analyzing data obtained from a database, A response generation means that generates a response based on the analysis results, A means of displaying the generated answer, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional building management system, specialized knowledge is required to obtain detailed data on facilities, and it is difficult for administrators to obtain the necessary information by themselves. In addition, it takes a lot of effort to analyze energy consumption, carbon dioxide emissions, calculate savings effects, etc., and efficient management is difficult. There is a need for a system that solves these problems, enables anyone to easily obtain the necessary information, and improves the efficiency of management operations.

Means for Solving the Problems

[0005] This invention provides a system that allows users to obtain necessary information simply by entering a question, comprising natural language input and natural language processing means for analyzing it. Specifically, it includes means for receiving questions entered in natural language, natural language processing means for analyzing the questions and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. As a result, administrators can intuitively obtain the necessary data without specialized knowledge and perform efficient building management.

[0006] "Natural language" refers to the language that humans use on a daily basis, and the process involves converting it into a format that computers can understand and process.

[0007] "Entered question" refers to the content of an inquiry that a user enters into their device using natural language.

[0008] "Means of receiving" refers to the functions or processes that allow the server to receive questions sent from a terminal.

[0009] "Natural language processing tools" refer to algorithms and programs that analyze questions entered in natural language, understand their context and intent, and extract necessary information.

[0010] "Query generation means" refers to a function that generates queries to query a database based on information extracted by natural language processing means.

[0011] A "database" refers to a central digital data storage device where various types of data related to a building are stored.

[0012] "Data analysis methods" refer to algorithms and programs used to evaluate data obtained from a database and obtain specific answers to user questions.

[0013] "Answer generation means" refers to a function that creates answers in a format that is easy for users to understand, based on the analysis results obtained by data analysis means.

[0014] "Means of display" refers to interfaces and functions that visually present the generated answers to the user.

[0015] A "building management system" refers to the entire system used to monitor and manage a building's energy consumption and equipment status. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0037] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0038] System Processing Overview

[0039] 1. User input of question

[0040] Users enter questions through a dedicated interface on the management terminal. For example, a possible format might be, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0041] 2. Sending from the terminal to the server

[0042] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[0043] 3. Server receives and analyzes the query.

[0044] The server passes the received question to a natural language processing (NLP) engine for analysis. For example, tokenization and morphological analysis are performed to understand the context of the question and extract the necessary information.

[0045] 4. Generating queries to the database

[0046] The server generates specific SQL queries for the database based on the information extracted by the NLP engine. For example, queries related to "last year's energy consumption" and "this year's energy consumption" are generated.

[0047] 5. Execute queries on the database

[0048] The server uses the generated SQL query to query the database. The database returns the necessary data.

[0049] 6. Data Analysis

[0050] The server analyzes the acquired data to obtain specific answers to the user's questions. For example, it calculates the difference in energy consumption and carbon dioxide emissions to determine the amount of savings.

[0051] 7. Generating the answer

[0052] The server generates responses in a user-friendly format based on the analysis results. For example, it might generate a response such as, "Energy consumption decreased by 10% compared to last year, resulting in savings of approximately 1 million yen."

[0053] 8. Sending responses from the server to the terminal.

[0054] The response generated by the server is sent to the user's management terminal as an HTTP response.

[0055] 9. Displaying responses via the device

[0056] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[0057] Specific example

[0058] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0059] 1. The user enters the question from the management terminal.

[0060] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[0061] 2. The terminal receives user input and sends it to the server.

[0062] 3. The server receives the question and analyzes it using the NLP engine.

[0063] 4. The server generates an SQL query based on the analysis results.

[0064] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0065] 5. The server sends a query to the database and retrieves the necessary data.

[0066] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0067] 7. The server generates an answer based on the analysis results.

[0068] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0069] 8. The server sends the generated response to the terminal.

[0070] 9. The device displays the received response.

[0071] This invention allows users to easily input questions in natural language and quickly obtain the necessary information, even without specialized knowledge. This system can significantly improve the efficiency of building management.

[0072] The following describes the processing flow.

[0073] Step 1:

[0074] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0075] Step 2:

[0076] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[0077] Step 3:

[0078] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[0079] Step 4:

[0080] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[0081] Step 5:

[0082] The server generates the necessary database queries based on the analysis results of the NLP engine. For example, it generates queries related to "last year's energy consumption" and "this year's energy consumption."

[0083] Step 6:

[0084] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0085] Step 7:

[0086] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[0087] Step 8:

[0088] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[0089] Step 9:

[0090] The server generates a response based on the analysis results. For example, it might create a specific response such as, "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0091] Step 10:

[0092] The server sends the generated response to the terminal as an HTTP response.

[0093] Step 11:

[0094] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[0095] (Example 1)

[0096] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] In modern building management, there is a demand for efficient management even for non-experts. However, current systems are difficult for users without specialized knowledge to operate, making it difficult to obtain information quickly and accurately. Furthermore, advanced technology is required to extract and analyze necessary information from vast amounts of data. Solving these problems is essential.

[0098] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0099] In this invention, the server includes means for receiving questions entered in natural language, natural language processing means for analyzing the questions and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for users to easily input questions in natural language and quickly and accurately obtain the necessary information, even without specialized knowledge.

[0100] "Natural language" refers to the language system that humans use on a daily basis, and is expressed through sound or writing.

[0101] "Means for receiving questions entered in natural language" refers to devices or software that receive questions entered by users in natural language and incorporate them into the system.

[0102] "Natural language processing means" refers to technologies and algorithms that analyze input natural language text, understand its context and meaning, and extract necessary information.

[0103] "Query generation means" refers to devices or software that generate query commands for a database based on analyzed information.

[0104] "Data analysis means" refers to processing devices or software used to analyze data obtained from a database and derive answers to user questions.

[0105] "Answer generation means" refers to devices or software that generate answers for the user based on analysis results.

[0106] "Means of display" refers to devices or software that display the generated answers in a way that users can verify.

[0107] "Tokenization" refers to the process of dividing natural language text into smaller units such as words and phrases.

[0108] Morphological analysis refers to the process of breaking down words into smaller parts and analyzing their basic forms in order to understand the meaning and role of each word that makes up a natural language text.

[0109] A "database" refers to a system for storing, efficiently managing, and retrieving collections of data.

[0110] "Energy consumption" refers to the amount of energy used over a specific period.

[0111] "Carbon dioxide emissions" refers to the amount of carbon dioxide emitted during a specific period.

[0112] "Difference" refers to the difference in quantity or numerical value between two things being compared.

[0113] "Savings" refers to the amount of money reduced by a particular action or measure.

[0114] An "HTTP request" is a protocol used by web browsers and other clients to request data from a server.

[0115] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0116] System Configuration

[0117] This invention comprises the following main components:

[0118] 1. Means for receiving questions entered in natural language.

[0119] The terminal receives questions entered by the user through a dedicated interface. These questions are in natural language and do not require any special formatting. For example, it accepts questions such as, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0120] 2. Natural Language Processing Means

[0121] The server passes the received question to a natural language processing (NLP) engine for analysis. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize and morphologically analyze the question, understand its context, and extract the necessary information.

[0122] 3. Query generation means

[0123] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." Specifically, it generates an SQL statement like this: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[0124] 4. Data Analysis Methods

[0125] The server uses the generated SQL query to query the database and retrieve the necessary data. Next, it analyzes that data, compares energy consumption and carbon dioxide emissions, and calculates the amount of savings.

[0126] 5. Answer generation means

[0127] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[0128] 6. Means for displaying the generated response

[0129] The device displays the received responses to the user. This allows the user to easily obtain specific answers to their questions.

[0130] Specific example

[0131] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0132] 1. The user enters the question from the management terminal.

[0133] "Have you reduced energy and carbon emissions compared to last year? How much money are you saving?"

[0134] 2. The terminal receives user input and sends it to the server.

[0135] 3. The server receives the question and analyzes it using an NLP engine. For example, it uses libraries such as spaCy or NLTK to perform tokenization and morphological analysis to understand the question.

[0136] 4. The server generates an SQL query based on the analysis results.

[0137] "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0138] 5. The server sends queries to the database and retrieves the necessary data. It uses a database management system such as MySQL® or PostgreSQL.

[0139] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0140] 7. The server generates an answer based on the analysis results.

[0141] "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[0142] 8. The server sends the generated response to the terminal.

[0143] 9. The device displays the received response to the user.

[0144] This allows users to easily input questions in natural language, even without specialized knowledge, and quickly and accurately obtain the information they need.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1: User enters question

[0147] Users enter questions in natural language using a dedicated interface on the management terminal. These questions do not require a special format as they are subject to natural language processing. For example, they might enter something like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0148] Input: Question in natural language format

[0149] Output: Data containing the question content

[0150] Step 2: Sending from the terminal to the server

[0151] The terminal receives the question entered by the user and sends it to the server as an HTTP request. This request contains the question and information related to the user.

[0152] Input: Data containing the question content

[0153] Output: HTTP request containing the question data

[0154] Step 3: Server receives and analyzes the question.

[0155] The server parses the received HTTP request and extracts the question content. Next, it passes the question to a natural language processing (NLP) engine for analysis. For example, it might tokenize the question using libraries such as spaCy or NLTK and then perform morphological analysis to understand the context.

[0156] Input: HTTP request (contains the question)

[0157] Output: Tokenized and morphologically analyzed question data

[0158] Step 4: Generate queries to the database

[0159] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." The specific SQL statements are as follows:

[0160] Example: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[0161] Input: Tokenized and morphologically analyzed question data

[0162] Output: SQL query against the database

[0163] Step 5: Execute queries on the database

[0164] The server sends the generated SQL query to the database and retrieves the necessary data. The database management system used is typically MySQL or PostgreSQL.

[0165] Input: SQL query

[0166] Output: Data retrieved from the database

[0167] Step 6: Data Analysis

[0168] The server analyzes the acquired data. Specifically, it compares energy consumption and carbon dioxide emissions from last year and this year, and calculates the amount of savings from the difference. This allows it to provide specific answers to user questions.

[0169] Input: Data retrieved from the database

[0170] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved)

[0171] Step 7: Generating the answer

[0172] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response like, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[0173] Input: Analysis results

[0174] Output: Generated answer

[0175] Step 8: Sending the response from the server to the terminal

[0176] The server sends the generated response to the terminal as an HTTP response.

[0177] Input: Generated answer

[0178] Output: HTTP response (response content)

[0179] Step 9: Displaying the response via the device

[0180] The terminal displays the received response on the user interface. This allows the user to easily obtain specific answers to their questions.

[0181] Input: HTTP response (response content)

[0182] Output: Answer displayed in the user interface

[0183] In this way, users can easily input questions in natural language without needing specialized knowledge, and quickly and accurately obtain the necessary information.

[0184] (Application Example 1)

[0185] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0186] In factory management, it is crucial for managers and workers to understand operating conditions and equipment status in real time. However, conventional systems require specialized knowledge, and data collection and analysis are time-consuming. Furthermore, the inability to easily ask and answer questions via voice input hinders efficient management. To solve these problems, a system is needed that accepts questions in natural language and provides quick and accurate answers.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0188] In this invention, the server includes means for receiving questions input by voice, voice recognition means for converting the questions into text, natural language processing means for analyzing the text and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for managers and workers to query the operating status of the factory and the status of equipment in real time using voice and obtain answers quickly and accurately.

[0189] "Means for receiving questions entered via voice" refers to a function that recognizes machine speech and captures that voice data.

[0190] "Speech recognition means" refers to a technology that analyzes received speech data and converts it into corresponding text.

[0191] "Natural language processing tools" are functions that analyze text-based questions, understand their context and content, and extract necessary information.

[0192] A "query generation method" is a technology that generates request statements, such as SQL queries, for querying a database based on information extracted through natural language processing.

[0193] A "data analysis tool" is a function that analyzes data obtained from a database and derives appropriate answers to questions.

[0194] "Answer generation method" refers to a technology that creates answers in a user-friendly format based on data analysis results.

[0195] "Means of display" refers to display devices or display software that provide the generated answers to the user visually.

[0196] This invention is a system for factory management that accepts questions using voice and provides answers in real time. This system enables factory managers and workers to efficiently understand the operating status and equipment status of the factory through voice.

[0197] The main components of this system include speech recognition software, a natural language processing engine, a database management system, and smart glasses. Specifically, it uses the following hardware and software:

[0198] Hardware to use

[0199] Smart glasses: Receiving and displaying voice input

[0200] Server: Data processing and database management

[0201] Software to use

[0202] Speech recognition software (e.g., Google® Cloud Speech-to-Text): Converts speech to text.

[0203] Natural language processing engines (e.g., SpaCy and NLTK): Question analysis

[0204] Database management system (e.g., MySQL): for storing data and executing queries.

[0205] The specific process of the system is as follows:

[0206] Voice input

[0207] Workers and managers input questions by voice into smart glasses. For example, questions could include, "How many machine malfunctions have there been this week?" or "What is the current energy consumption?"

[0208] Speech recognition

[0209] The smart glasses convert the input audio into text using speech recognition software and send that text data to a server.

[0210] question analysis

[0211] The server analyzes the received text data using a natural language processing engine to understand the context and content of the question and extract the necessary information. For example, it performs tokenization and morphological analysis to obtain specific information for querying the database.

[0212] Query generation and data retrieval

[0213] Based on the analysis results, an SQL query is generated for the database. The server uses this query to retrieve the necessary data from the database.

[0214] Data analysis and response generation

[0215] The server analyzes the data obtained from the database and generates specific answers to the questions. For example, it might generate an answer such as, "There have been 3 machine failures this week, and the current energy consumption is 1000kWh."

[0216] Display the answer

[0217] The generated response is sent from the server to the smart glasses and displayed on the screen.

[0218] Specific example

[0219] When an administrator asks, "Please tell me the machine's operating hours for this month," the system processes the request using the following steps:

[0220] 1. Recognize speech and convert it to text.

[0221] 2. Analyze the relevant text using natural language processing.

[0222] 3. Send a query to the database and retrieve the necessary data.

[0223] 4. Analyze the obtained data and generate the answer.

[0224] 5. Display the answer on smart glasses.

[0225] Example of a prompt

[0226] "I'd like to know the operating hours for each machine this month."

[0227] "Please tell me the number of malfunctions that occurred this month."

[0228] As a result, this system allows managers and workers to efficiently perform factory management tasks.

[0229] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0230] Step 1:

[0231] The user inputs a question by voice into the smart glasses. For example, they might say, "How many machine failures were there this week?" At this point, the input is the user's voice.

[0232] Step 2:

[0233] Smart glasses use speech recognition software (e.g., Google Cloud Speech-to-Text) to convert speech to text. They analyze the speech data and generate corresponding text data. The output is the corresponding text data.

[0234] Step 3:

[0235] The terminal sends the generated text data to the server as an HTTP request. The input is text data, and the output is an HTTP request.

[0236] Step 4:

[0237] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). Specifically, it performs tokenization and morphological analysis to extract the context and keywords of the question. The input is text data, and the output is the extracted keywords and contextual information.

[0238] Step 5:

[0239] The server generates an SQL query to query the database based on the extracted information. For example, a query like "SELECT COUNT() FROM malfunction_logs WHERE week = 'current_week';" is generated. The input is the extracted information, and the output is the generated SQL query.

[0240] Step 6:

[0241] The server sends the generated SQL query to the database management system (e.g., MySQL) and retrieves the necessary data. The input is the SQL query, and the output is the data returned from the database.

[0242] Step 7:

[0243] The server analyzes the acquired data using data analysis tools and generates specific answers to questions. For example, it might generate an answer such as, "There were 3 machine failures this week." The input is data obtained from the database, and the output is the generated answer.

[0244] Step 8:

[0245] The server sends the generated response to the smart glasses as an HTTP response. The input is the generated response, and the output is the HTTP response.

[0246] Step 9:

[0247] The smart glasses display the received response as text data on the screen. The input is the response as an HTTP response, and the output is the text displayed on the screen.

[0248] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0249] This invention relates to a building management system that analyzes questions entered in natural language and the user's emotions, acquires and analyzes necessary data, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0250] System Processing Overview

[0251] 1. User input of question

[0252] Users enter questions through a dedicated interface on the management terminal. For example, they might enter a question like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0253] 2. Sending from the terminal to the server

[0254] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[0255] 3. Server receives and analyzes the query.

[0256] The server passes the received question to a natural language processing (NLP) engine and an emotion engine for analysis. The NLP engine understands the context of the question and extracts the necessary information. The emotion engine recognizes the user's emotions as expressed in the question.

[0257] 4. Generating queries to the database

[0258] The server generates specific SQL queries for the database based on the information extracted by the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[0259] 5. Execute queries on the database

[0260] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0261] 6. Data Analysis

[0262] The server analyzes the acquired data to obtain specific analysis results regarding the user's questions and emotions. This includes comparisons of differences in energy consumption and carbon dioxide emissions.

[0263] 7. Generating the answer

[0264] The server generates responses based on analysis results and the user's emotional state. For example, it might create a specific response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen." The emotion engine adjusts the tone and expression of the response according to the user's emotions.

[0265] 8. Sending responses from the server to the terminal.

[0266] The response generated by the server is sent to the user's management terminal as an HTTP response.

[0267] 9. Displaying responses via the device

[0268] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[0269] Specific example

[0270] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0271] 1. The user enters the question from the management terminal.

[0272] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[0273] 2. The terminal receives user input and sends it to the server.

[0274] 3. The server receives the question and analyzes it using the NLP engine and the emotion engine.

[0275] The NLP engine understands the context and extracts the necessary information. The emotion engine recognizes the user's emotions.

[0276] 4. The server generates an SQL query based on the analysis results.

[0277] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0278] 5. The server sends a query to the database and retrieves the necessary data.

[0279] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0280] 7. The server generates a response based on the analysis results and the user's emotional state.

[0281] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0282] 8. The server sends the generated response to the terminal.

[0283] 9. The device displays the received response.

[0284] According to the present invention, even without specialized knowledge, a user can easily input questions in natural language and quickly obtain the necessary information. Furthermore, since the emotion engine provides answers according to the user's emotions, the user experience is improved. This system can greatly improve the efficiency of building management.

[0285] The processing flow will be described below.

[0286] Step 1:

[0287] The user inputs a question from the dedicated interface of the management terminal. As an example, a question such as "Have the energy and carbon dioxide emissions been reduced compared to last year? How much money can be saved?" is input.

[0288] Step 2:

[0289] The terminal receives the user's input and sends the question content to the server in the form of an HTTP request. The request includes the question content and user-related information.

[0290] Step 3:

[0291] The server analyzes the received request and passes the question to the natural language processing (NLP) engine. This prepares to understand the context of the question and extract the necessary information.

[0292] Step 4:

[0293] The server's NLP engine tokenizes the question and performs morphological analysis. This process decomposes each part of the question and analyzes the context and meaning.

[0294] Step 5:

[0295] The server's emotion engine analyzes the user's emotional elements included in the question. This enables understanding of the user's emotional state when asking the question.

[0296] Step 6:

[0297] The server generates the necessary database queries based on the analysis results of the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[0298] Step 7:

[0299] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0300] Step 8:

[0301] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[0302] Step 9:

[0303] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[0304] Step 10:

[0305] The server generates a response based on the analysis results. In this process, it uses the results of the emotion engine to generate a response with a tone and language appropriate to the user's emotional state. For example, it might create a specific and considerate response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen."

[0306] Step 11:

[0307] The server sends the generated response to the terminal as an HTTP response.

[0308] Step 12:

[0309] The terminal displays the received answer on the user interface. Through the displayed answer, the user can easily understand the information regarding the question.

[0310] (Example 2)

[0311] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0312] In building management, there is a need for means by which users can efficiently and effectively obtain and manage information without having specialized knowledge. However, conventional systems require complex operations and specialized knowledge, which may pose an obstacle to daily operations. In addition, it is difficult to provide a prompt answer considering the user's feelings, and improving the user experience is also an issue.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0314] In this invention, the server includes means for receiving a question input in natural language, natural language processing means for analyzing the question to extract necessary information, sentiment analysis means for analyzing the user's sentiment included in the question, query generation means for querying a database based on the extracted information, data analysis means for analyzing the data obtained from the database, answer generation means for generating an answer in consideration of the user's sentiment based on the analysis result, and means for displaying the generated answer. Thereby, the user can input a question in natural language, quickly obtain the necessary information without requiring specialized knowledge, and it becomes possible to provide an answer according to the user's sentiment.

[0315] The "means for receiving a question input in natural language" is an interface for receiving text data input in natural language from the user.

[0316] "Natural language processing means" refers to technologies for analyzing received natural language text data and extracting intent and important information.

[0317] "Emotion analysis methods" are technologies that analyze a user's emotions from natural language text data and identify their emotional state.

[0318] A "query generation method" is a technology that generates query statements (SQL queries) to be executed against a database based on the analyzed information.

[0319] "Data analysis methods" refer to techniques for analyzing data obtained from databases and extracting and calculating useful information.

[0320] "Answer generation means" refers to a technology for generating responses to users in natural language form based on analyzed data and the user's emotional state.

[0321] "Means for displaying generated answers" refers to an interface for visually displaying generated answers to the user.

[0322] This invention relates to a building management system that analyzes questions entered by users in natural language and provides appropriate answers to those questions. This system is designed to enable efficient building management even for users without specialized knowledge.

[0323] Hardware and software to use

[0324] The main hardware and software components of this system include:

[0325] Management terminal: A device that provides an interface for users to enter questions. Examples include PCs, tablets, and smartphones.

[0326] Server: The primary device responsible for parsing questions, generating queries to the database, performing data analysis, and generating answers.

[0327] Natural language processing engine: Software such as the Google Cloud Natural Language API that analyzes questions and extracts important information.

[0328] Emotion analysis engine: Software for analyzing user emotions, such as IBM Watson® Tone Analyzer.

[0329] Database: A database that stores data on a building's energy consumption and carbon dioxide emissions.

[0330] Interface software: Software that retrieves questions entered by the user, sends them to the server, and receives and displays the answers from the server.

[0331] Specific operation of the system

[0332] Users input questions in natural language using a dedicated interface on the management terminal. For example, they might input a question like, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0333] The management terminal retrieves this question as text data and sends it to the server as an HTTP request. This request includes the question content and user-related identification information.

[0334] The server passes the received question to a natural language processing engine and an emotion analysis engine for analysis. The natural language processing engine understands the context of the question and extracts important information. The emotion analysis engine analyzes the user's emotions and understands the user's state.

[0335] Based on the analyzed information, the server generates a specific SQL query to execute against the database. For example, it might generate a query like "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X".

[0336] The server sends the generated query to the database and retrieves the necessary data. The retrieved data is then analyzed by data analysis tools, for example, to compare energy consumption and carbon dioxide emissions, and to calculate savings.

[0337] The server generates specific responses in natural language based on the analysis results and the user's emotional state. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[0338] The generated response is sent to the management terminal as an HTTP response. The management terminal receives this response and displays it visually to the user.

[0339] Examples of specific cases and prompt statements

[0340] As a concrete example, the following prompt statements are possible:

[0341] Question: "Have you reduced energy and carbon dioxide emissions compared to last year? How much money are you saving?"

[0342] Answer: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[0343] This invention allows users to input questions in natural language without requiring specialized knowledge of building management, and to obtain quick and appropriate answers. Furthermore, the emotion analysis engine provides answers that respond to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[0344] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0345] Step 1:

[0346] User input of question

[0347] User: Use the dedicated interface on the management terminal to enter questions in natural language. For example, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0348] Input: Text data entered in natural language.

[0349] Output: The question text displayed on the interface.

[0350] Step 2:

[0351] Sending from the terminal to the server

[0352] Terminal: Retrieves the user's input as text data, generates an HTTP request, and sends it to the server.

[0353] Input: Text data of the question.

[0354] Output: HTTP request containing the question content.

[0355] Step 3:

[0356] Server receives and analyzes questions.

[0357] Server: Parses the received HTTP request and extracts the question as text. This is then passed to the natural language processing engine and sentiment analysis engine for analysis.

[0358] Server: Uses a natural language processing engine (e.g., Google Cloud Natural Language API) to understand the context of the question and extract important information.

[0359] Server: Uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to identify the user's emotions.

[0360] Input: HTTP request containing the question content.

[0361] Output: Analyzed information (keywords, context, emotional state).

[0362] Step 4:

[0363] Generating queries to the database

[0364] Server: Generates SQL queries to the database based on information obtained from the NLP engine and emotion engine. For example, queries to retrieve "last year's energy consumption" or "this year's energy consumption".

[0365] Input: Analyzed information (keywords, context, emotional state).

[0366] Output: The generated SQL query.

[0367] Step 5:

[0368] Execute queries against the database

[0369] Server: Uses the generated SQL query to query the database and retrieve the necessary data.

[0370] Server: Establishes a database connection and executes queries while handling errors.

[0371] Input: SQL query.

[0372] Output: Data retrieved from the database.

[0373] Step 6:

[0374] Data Analysis

[0375] Server: Analyzes data obtained from the database to compare energy consumption and carbon dioxide emissions, and calculate savings.

[0376] Server: Performs calculations and calculates the difference and savings.

[0377] Input: Data retrieved from a database.

[0378] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved).

[0379] Step 7:

[0380] Answer generation

[0381] Server: Based on the analysis results and the user's emotional state, it generates specific responses in natural language. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions have decreased by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[0382] Input: Analysis results, user's emotional state.

[0383] Output: Generated answer text.

[0384] Step 8:

[0385] Sending responses from the server to the terminal.

[0386] Server: Sends the generated response text to the management terminal as an HTTP response.

[0387] Server: Formats the response into JSON format or similar and generates an HTTP response.

[0388] Input: Generated response text.

[0389] Output: HTTP response.

[0390] Step 9:

[0391] Displaying responses via device

[0392] Terminal: Analyzes the HTTP response received from the server and displays it to the user in a visually easy-to-understand format. For example, it might display: "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen."

[0393] Input: HTTP response.

[0394] Output: The answer text displayed on the terminal.

[0395] (Application Example 2)

[0396] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0397] Traditional building management systems made it difficult for users without specialized knowledge to effectively utilize the system. Furthermore, the lack of means to provide quick and appropriate answers to user questions hindered the user experience. This made it particularly difficult to obtain information regarding energy management and production efficiency, impeding the efficiency of management operations. Additionally, the failure to consider user emotions in response generation resulted in low user satisfaction.

[0398] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving a question input in natural language, natural language processing means for analyzing the question and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer based on the analysis results, means for displaying the generated answer, and sentiment analysis means for analyzing the user's emotions. As a result, the user can quickly obtain specific information regarding energy management and production efficiency through questions in natural language without specialized knowledge. In addition, the user experience is improved because appropriate answers are provided based on the user's emotions.

[0399] "Natural language" refers to the language that humans use on a daily basis, and is a means of conveying information in the form of writing and conversation.

[0400] "Natural language processing means" refers to technologies for analyzing natural language, such as questions and commands, and extracting necessary information.

[0401] A "query generation method" is a means of generating a query for a database based on the extracted information.

[0402] "Data analysis methods" refer to techniques for analyzing data obtained from databases to derive useful information and trends.

[0403] A "response generation method" is a means of generating responses for users based on the results of data analysis.

[0404] "Display means" refers to a means of displaying the generated response so that the user can confirm it.

[0405] An "emotion analysis tool" is a means of analyzing the user's emotions contained in questions and commands, and enabling responses that correspond to those emotions.

[0406] "Energy consumption" refers to the total amount of energy consumed within a certain period.

[0407] "Carbon dioxide emissions" refers to the total amount of carbon dioxide emitted within a certain period.

[0408] "Production efficiency" is an indicator that represents the efficiency of production results in relation to the resources invested in a factory or production line.

[0409] A "factory management system" is a system that comprehensively handles the information necessary for the operation and management of a factory, and supports efficient operations.

[0410] This invention relates to a building management system that analyzes questions entered in natural language, retrieves necessary information from a database, analyzes it, generates answers, and takes user emotions into consideration. Specific embodiments for carrying out this invention are described below.

[0411] The system primarily uses the following hardware and software:

[0412] Server (question analysis and data processing)

[0413] Smartphone (user device)

[0414] Database server (data storage)

[0415] The specific software used includes the following:

[0416] Natural Language Processing Engine (NLPEngine)

[0417] Sentiment Engine

[0418] Database connection library (MySQL Connector)

[0419] The user inputs a question in natural language from their smartphone. For example, they might input, "How much did this month's energy consumption increase compared to last month, and what was the reason?" The smartphone receives the question and sends it to the server as an HTTP request. Upon receiving the question, the server automatically uses NLPEngine to analyze the context of the question. NLPEngine performs tokenization and morphological analysis to extract the necessary information from the question.

[0420] Next, the server uses a SentimentEngine to analyze the user's emotions. This identifies the emotional elements contained in the question. Based on the analyzed information, an SQL query is generated for the database. The generated query is sent to the database server, and the necessary data is retrieved.

[0421] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. For example, it can determine how much energy consumption has increased compared to the previous month, and whether the cause is the introduction of a new production line.

[0422] Based on the analysis results, the response generation system generates an appropriate response for the user. Using an emotion analysis engine, the response is adjusted to a tone that matches the user's emotions. For example, "This month's energy consumption has increased by 10% compared to last month. The main reason is the introduction of a new production line."

[0423] The generated response is sent from the server to the user's smartphone as an HTTP response. The smartphone then displays the received response to the user. This allows users, even without specialized knowledge, to quickly obtain information on energy management and production efficiency using natural language and utilize it in their management activities.

[0424] As a concrete example, when the question "How much did this month's energy consumption increase compared to last month, and what was the reason?" is entered, the system, after going through the aforementioned analysis flow, generates the answer "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." Based on the same question, the AI ​​model can be given example prompts such as "Please tell me the reason for the fluctuation in the factory's energy consumption" and "What caused the increase in energy consumption compared to last month?"

[0425] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0426] Step 1:

[0427] The user enters a question from their smartphone. For example, they might enter, "How much did this month's energy consumption increase compared to last month, and what was the reason?" In this case, the smartphone receives the question in natural language as input and displays the question on the smartphone as output.

[0428] Step 2:

[0429] The device (smartphone) sends the received question to the server as an HTTP request. This request includes the question content and user-specific information. It receives a request containing a natural language question and user information as input, and sends that request to the server as output.

[0430] Step 3:

[0431] The server receives an HTTP request and uses a natural language processing engine (NLPEngine) to analyze the context of the question. Specifically, it tokenizes the natural language question received as input, performs morphological analysis, and understands the context of the question. As a result, the necessary information is extracted, and the extracted information is obtained as output.

[0432] Step 4:

[0433] The server uses a SentimentEngine to analyze the user's emotions. Based on the questions received as input, emotion analysis is performed, and the user's emotional state is identified. The user's emotion data is obtained as output.

[0434] Step 5:

[0435] The server generates an SQL query to the database based on the extracted information and sentiment data. It takes the extracted information and sentiment data as input and outputs the generated SQL query. For example, a query like "SELECT energy_last_month, energy_this_month, reason FROM factory_energy_data WHERE factory_id = X;" is generated.

[0436] Step 6:

[0437] The server sends the generated SQL query to the database server and retrieves the necessary data. It receives the generated SQL query as input and queries the database server. The retrieved data is obtained as output.

[0438] Step 7:

[0439] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. It receives acquired data as input and performs data analysis such as calculating fluctuations in energy consumption and savings. The analysis results are obtained as output.

[0440] Step 8:

[0441] The server generates responses based on analysis results and user sentiment data. It receives analysis results and sentiment data as input and adjusts the response to match the user's sentiment. For example, it might generate a response such as, "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." The generated response is obtained as output.

[0442] Step 9:

[0443] The server sends the generated response to the user's smartphone as an HTTP response. It receives the generated response as input and sends that response to the smartphone as output.

[0444] Step 10:

[0445] The device (smartphone) displays the received response to the user. It receives the response as input and displays that response on the smartphone screen as output. This allows the user to obtain a specific answer to the question.

[0446] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0447] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0448] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0449] [Second Embodiment]

[0450] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0451] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0452] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0453] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0454] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0455] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0456] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0457] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0458] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0459] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0460] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0461] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0462] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0463] System Processing Overview

[0464] 1. User input of question

[0465] Users enter questions through a dedicated interface on the management terminal. For example, a possible format might be, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0466] 2. Sending from the terminal to the server

[0467] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[0468] 3. Server receives and analyzes the query.

[0469] The server passes the received question to a natural language processing (NLP) engine for analysis. For example, tokenization and morphological analysis are performed to understand the context of the question and extract the necessary information.

[0470] 4. Generating queries to the database

[0471] The server generates specific SQL queries for the database based on the information extracted by the NLP engine. For example, queries related to "last year's energy consumption" and "this year's energy consumption" are generated.

[0472] 5. Execute queries on the database

[0473] The server uses the generated SQL query to query the database. The database returns the necessary data.

[0474] 6. Data Analysis

[0475] The server analyzes the acquired data to obtain specific answers to the user's questions. For example, it calculates the difference in energy consumption and carbon dioxide emissions to determine the amount of savings.

[0476] 7. Generating the answer

[0477] The server generates responses in a user-friendly format based on the analysis results. For example, it might generate a response such as, "Energy consumption decreased by 10% compared to last year, resulting in savings of approximately 1 million yen."

[0478] 8. Sending responses from the server to the terminal.

[0479] The response generated by the server is sent to the user's management terminal as an HTTP response.

[0480] 9. Displaying responses via the device

[0481] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[0482] Specific example

[0483] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0484] 1. The user enters the question from the management terminal.

[0485] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[0486] 2. The terminal receives user input and sends it to the server.

[0487] 3. The server receives the question and analyzes it using the NLP engine.

[0488] 4. The server generates an SQL query based on the analysis results.

[0489] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0490] 5. The server sends a query to the database and retrieves the necessary data.

[0491] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0492] 7. The server generates an answer based on the analysis results.

[0493] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0494] 8. The server sends the generated response to the terminal.

[0495] 9. The device displays the received response.

[0496] This invention allows users to easily input questions in natural language and quickly obtain the necessary information, even without specialized knowledge. This system can significantly improve the efficiency of building management.

[0497] The following describes the processing flow.

[0498] Step 1:

[0499] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0500] Step 2:

[0501] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[0502] Step 3:

[0503] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[0504] Step 4:

[0505] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[0506] Step 5:

[0507] The server generates the necessary database queries based on the analysis results of the NLP engine. For example, it generates queries related to "last year's energy consumption" and "this year's energy consumption."

[0508] Step 6:

[0509] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0510] Step 7:

[0511] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[0512] Step 8:

[0513] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[0514] Step 9:

[0515] The server generates a response based on the analysis results. For example, it might create a specific response such as, "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0516] Step 10:

[0517] The server sends the generated response to the terminal as an HTTP response.

[0518] Step 11:

[0519] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[0520] (Example 1)

[0521] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0522] In modern building management, there is a demand for efficient management even for non-experts. However, current systems are difficult for users without specialized knowledge to operate, making it difficult to obtain information quickly and accurately. Furthermore, advanced technology is required to extract and analyze necessary information from vast amounts of data. Solving these problems is essential.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0524] In this invention, the server includes means for receiving questions entered in natural language, natural language processing means for analyzing the questions and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for users to easily input questions in natural language and quickly and accurately obtain the necessary information, even without specialized knowledge.

[0525] "Natural language" refers to the language system that humans use on a daily basis, and is expressed through sound or writing.

[0526] "Means for receiving questions entered in natural language" refers to devices or software that receive questions entered by users in natural language and incorporate them into the system.

[0527] "Natural language processing means" refers to technologies and algorithms that analyze input natural language text, understand its context and meaning, and extract necessary information.

[0528] "Query generation means" refers to devices or software that generate query commands for a database based on analyzed information.

[0529] "Data analysis means" refers to processing devices or software used to analyze data obtained from a database and derive answers to user questions.

[0530] "Answer generation means" refers to devices or software that generate answers for the user based on analysis results.

[0531] "Means of display" refers to devices or software that display the generated answers in a way that users can verify.

[0532] "Tokenization" refers to the process of dividing natural language text into smaller units such as words and phrases.

[0533] Morphological analysis refers to the process of breaking down words into smaller parts and analyzing their basic forms in order to understand the meaning and role of each word that makes up a natural language text.

[0534] A "database" refers to a system for storing, efficiently managing, and retrieving collections of data.

[0535] "Energy consumption" refers to the amount of energy used over a specific period.

[0536] "Carbon dioxide emissions" refers to the amount of carbon dioxide emitted during a specific period.

[0537] "Difference" refers to the difference in quantity or numerical value between two things being compared.

[0538] "Savings" refers to the amount of money reduced by a particular action or measure.

[0539] An "HTTP request" is a protocol used by web browsers and other clients to request data from a server.

[0540] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0541] System Configuration

[0542] This invention comprises the following main components:

[0543] 1. Means for receiving questions entered in natural language.

[0544] The terminal receives questions entered by the user through a dedicated interface. These questions are in natural language and do not require any special formatting. For example, it accepts questions such as, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0545] 2. Natural Language Processing Means

[0546] The server passes the received question to a natural language processing (NLP) engine for analysis. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize and morphologically analyze the question, understand its context, and extract the necessary information.

[0547] 3. Query generation means

[0548] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." Specifically, it generates an SQL statement like this: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[0549] 4. Data Analysis Methods

[0550] The server uses the generated SQL query to query the database and retrieve the necessary data. Next, it analyzes that data, compares energy consumption and carbon dioxide emissions, and calculates the amount of savings.

[0551] 5. Answer generation means

[0552] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[0553] 6. Means for displaying the generated response

[0554] The device displays the received responses to the user. This allows the user to easily obtain specific answers to their questions.

[0555] Specific example

[0556] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0557] 1. The user enters the question from the management terminal.

[0558] "Have you reduced energy and carbon emissions compared to last year? How much money are you saving?"

[0559] 2. The terminal receives user input and sends it to the server.

[0560] 3. The server receives the question and analyzes it using an NLP engine. For example, it uses libraries such as spaCy or NLTK to perform tokenization and morphological analysis to understand the question.

[0561] 4. The server generates an SQL query based on the analysis results.

[0562] "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0563] 5. The server sends queries to the database and retrieves the necessary data. A database management system such as MySQL or PostgreSQL is used.

[0564] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0565] 7. The server generates an answer based on the analysis results.

[0566] "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[0567] 8. The server sends the generated response to the terminal.

[0568] 9. The device displays the received response to the user.

[0569] This allows users to easily input questions in natural language, even without specialized knowledge, and quickly and accurately obtain the information they need.

[0570] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0571] Step 1: User enters question

[0572] Users enter questions in natural language using a dedicated interface on the management terminal. These questions do not require a special format as they are subject to natural language processing. For example, they might enter something like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0573] Input: Question in natural language format

[0574] Output: Data containing the question content

[0575] Step 2: Sending from the terminal to the server

[0576] The terminal receives the question entered by the user and sends it to the server as an HTTP request. This request contains the question and information related to the user.

[0577] Input: Data containing the question content

[0578] Output: HTTP request containing the question data

[0579] Step 3: Server receives and analyzes the question.

[0580] The server parses the received HTTP request and extracts the question content. Next, it passes the question to a natural language processing (NLP) engine for analysis. For example, it might tokenize the question using libraries such as spaCy or NLTK and then perform morphological analysis to understand the context.

[0581] Input: HTTP request (contains the question)

[0582] Output: Tokenized and morphologically analyzed question data

[0583] Step 4: Generate queries to the database

[0584] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." The specific SQL statements are as follows:

[0585] Example: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[0586] Input: Tokenized and morphologically analyzed question data

[0587] Output: SQL query against the database

[0588] Step 5: Execute queries on the database

[0589] The server sends the generated SQL query to the database and retrieves the necessary data. The database management system used is typically MySQL or PostgreSQL.

[0590] Input: SQL query

[0591] Output: Data retrieved from the database

[0592] Step 6: Data Analysis

[0593] The server analyzes the acquired data. Specifically, it compares energy consumption and carbon dioxide emissions from last year and this year, and calculates the amount of savings from the difference. This allows it to provide specific answers to user questions.

[0594] Input: Data retrieved from the database

[0595] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved)

[0596] Step 7: Generating the answer

[0597] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response like, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[0598] Input: Analysis results

[0599] Output: Generated answer

[0600] Step 8: Sending the response from the server to the terminal

[0601] The server sends the generated response to the terminal as an HTTP response.

[0602] Input: Generated answer

[0603] Output: HTTP response (response content)

[0604] Step 9: Displaying the response via the device

[0605] The terminal displays the received response on the user interface. This allows the user to easily obtain specific answers to their questions.

[0606] Input: HTTP response (response content)

[0607] Output: Answer displayed in the user interface

[0608] In this way, users can easily input questions in natural language without needing specialized knowledge, and quickly and accurately obtain the necessary information.

[0609] (Application Example 1)

[0610] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0611] In factory management, it is crucial for managers and workers to understand operating conditions and equipment status in real time. However, conventional systems require specialized knowledge, and data collection and analysis are time-consuming. Furthermore, the inability to easily ask and answer questions via voice input hinders efficient management. To solve these problems, a system is needed that accepts questions in natural language and provides quick and accurate answers.

[0612] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0613] In this invention, the server includes means for receiving questions input by voice, voice recognition means for converting the questions into text, natural language processing means for analyzing the text and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for managers and workers to query the operating status of the factory and the status of equipment in real time using voice and obtain answers quickly and accurately.

[0614] "Means for receiving questions entered via voice" refers to a function that recognizes machine speech and captures that voice data.

[0615] "Speech recognition means" refers to a technology that analyzes received speech data and converts it into corresponding text.

[0616] "Natural language processing tools" are functions that analyze text-based questions, understand their context and content, and extract necessary information.

[0617] A "query generation method" is a technology that generates request statements, such as SQL queries, for querying a database based on information extracted through natural language processing.

[0618] A "data analysis tool" is a function that analyzes data obtained from a database and derives appropriate answers to questions.

[0619] "Answer generation method" refers to a technology that creates answers in a user-friendly format based on data analysis results.

[0620] "Means of display" refers to display devices or display software that provide the generated answers to the user visually.

[0621] This invention is a system for factory management that accepts questions using voice and provides answers in real time. This system enables factory managers and workers to efficiently understand the operating status and equipment status of the factory through voice.

[0622] The main components of this system include speech recognition software, a natural language processing engine, a database management system, and smart glasses. Specifically, it uses the following hardware and software:

[0623] Hardware to use

[0624] Smart glasses: Receiving and displaying voice input

[0625] Server: Data processing and database management

[0626] Software to use

[0627] Speech recognition software (e.g., Google Cloud Speech-to-Text): Converts speech to text.

[0628] Natural language processing engines (e.g., SpaCy and NLTK): Question analysis

[0629] Database management system (e.g., MySQL): for storing data and executing queries.

[0630] The specific process of the system is as follows:

[0631] Voice input

[0632] Workers and managers input questions by voice into smart glasses. For example, questions could include, "How many machine malfunctions have there been this week?" or "What is the current energy consumption?"

[0633] Speech recognition

[0634] The smart glasses convert the input audio into text using speech recognition software and send that text data to a server.

[0635] question analysis

[0636] The server analyzes the received text data using a natural language processing engine to understand the context and content of the question and extract the necessary information. For example, it performs tokenization and morphological analysis to obtain specific information for querying the database.

[0637] Query generation and data retrieval

[0638] Based on the analysis results, an SQL query is generated for the database. The server uses this query to retrieve the necessary data from the database.

[0639] Data analysis and response generation

[0640] The server analyzes the data obtained from the database and generates specific answers to the questions. For example, it might generate an answer such as, "There have been 3 machine failures this week, and the current energy consumption is 1000kWh."

[0641] Display the answer

[0642] The generated response is sent from the server to the smart glasses and displayed on the screen.

[0643] Specific example

[0644] When an administrator asks, "Please tell me the machine's operating hours for this month," the system processes the request using the following steps:

[0645] 1. Recognize speech and convert it to text.

[0646] 2. Analyze the relevant text using natural language processing.

[0647] 3. Send a query to the database and retrieve the necessary data.

[0648] 4. Analyze the obtained data and generate the answer.

[0649] 5. Display the answer on smart glasses.

[0650] Example of a prompt

[0651] "I'd like to know the operating hours for each machine this month."

[0652] "Please tell me the number of malfunctions that occurred this month."

[0653] As a result, this system allows managers and workers to efficiently perform factory management tasks.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The user inputs a question by voice into the smart glasses. For example, they might say, "How many machine failures were there this week?" At this point, the input is the user's voice.

[0657] Step 2:

[0658] Smart glasses use speech recognition software (e.g., Google Cloud Speech-to-Text) to convert speech to text. They analyze the speech data and generate corresponding text data. The output is the corresponding text data.

[0659] Step 3:

[0660] The terminal sends the generated text data to the server as an HTTP request. The input is text data, and the output is an HTTP request.

[0661] Step 4:

[0662] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). Specifically, it performs tokenization and morphological analysis to extract the context and keywords of the question. The input is text data, and the output is the extracted keywords and contextual information.

[0663] Step 5:

[0664] The server generates an SQL query to query the database based on the extracted information. For example, a query like "SELECT COUNT() FROM malfunction_logs WHERE week = 'current_week';" is generated. The input is the extracted information, and the output is the generated SQL query.

[0665] Step 6:

[0666] The server sends the generated SQL query to the database management system (e.g., MySQL) and retrieves the necessary data. The input is the SQL query, and the output is the data returned from the database.

[0667] Step 7:

[0668] The server analyzes the acquired data using data analysis tools and generates specific answers to questions. For example, it might generate an answer such as, "There were 3 machine failures this week." The input is data obtained from the database, and the output is the generated answer.

[0669] Step 8:

[0670] The server sends the generated response to the smart glasses as an HTTP response. The input is the generated response, and the output is the HTTP response.

[0671] Step 9:

[0672] The smart glasses display the received response as text data on the screen. The input is the response as an HTTP response, and the output is the text displayed on the screen.

[0673] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0674] This invention relates to a building management system that analyzes questions entered in natural language and the user's emotions, acquires and analyzes necessary data, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0675] System Processing Overview

[0676] 1. User input of question

[0677] Users enter questions through a dedicated interface on the management terminal. For example, they might enter a question like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0678] 2. Sending from the terminal to the server

[0679] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[0680] 3. Server receives and analyzes the query.

[0681] The server passes the received question to a natural language processing (NLP) engine and an emotion engine for analysis. The NLP engine understands the context of the question and extracts the necessary information. The emotion engine recognizes the user's emotions as expressed in the question.

[0682] 4. Generating queries to the database

[0683] The server generates specific SQL queries for the database based on the information extracted by the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[0684] 5. Execute queries on the database

[0685] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0686] 6. Data Analysis

[0687] The server analyzes the acquired data to obtain specific analysis results regarding the user's questions and emotions. This includes comparisons of differences in energy consumption and carbon dioxide emissions.

[0688] 7. Generating the answer

[0689] The server generates responses based on analysis results and the user's emotional state. For example, it might create a specific response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen." The emotion engine adjusts the tone and expression of the response according to the user's emotions.

[0690] 8. Sending responses from the server to the terminal.

[0691] The response generated by the server is sent to the user's management terminal as an HTTP response.

[0692] 9. Displaying responses via the device

[0693] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[0694] Specific example

[0695] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0696] 1. The user enters the question from the management terminal.

[0697] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[0698] 2. The terminal receives user input and sends it to the server.

[0699] 3. The server receives the question and analyzes it using the NLP engine and the emotion engine.

[0700] The NLP engine understands the context and extracts the necessary information. The emotion engine recognizes the user's emotions.

[0701] 4. The server generates an SQL query based on the analysis results.

[0702] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0703] 5. The server sends a query to the database and retrieves the necessary data.

[0704] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0705] 7. The server generates a response based on the analysis results and the user's emotional state.

[0706] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0707] 8. The server sends the generated response to the terminal.

[0708] 9. The device displays the received response.

[0709] This invention allows users to easily input questions in natural language and quickly obtain necessary information, even without specialized knowledge. Furthermore, the emotion engine provides responses tailored to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0713] Step 2:

[0714] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[0715] Step 3:

[0716] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[0717] Step 4:

[0718] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[0719] Step 5:

[0720] The server's sentiment engine analyzes the user's emotional elements contained in the question. This allows the server to understand the user's emotional state at the time the question was asked.

[0721] Step 6:

[0722] The server generates the necessary database queries based on the analysis results of the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[0723] Step 7:

[0724] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0725] Step 8:

[0726] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[0727] Step 9:

[0728] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[0729] Step 10:

[0730] The server generates a response based on the analysis results. In this process, it uses the results of the emotion engine to generate a response with a tone and language appropriate to the user's emotional state. For example, it might create a specific and considerate response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen."

[0731] Step 11:

[0732] The server sends the generated response to the terminal as an HTTP response.

[0733] Step 12:

[0734] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[0735] (Example 2)

[0736] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0737] In building management, there is a need for a means that allows users to efficiently and effectively acquire and manage information without requiring specialized knowledge. However, conventional systems require complex operations and specialized knowledge, which can hinder daily operations. Furthermore, providing quick responses that take user emotions into consideration is difficult, and improving the user experience is also a challenge.

[0738] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0739] In this invention, the server includes means for receiving a question entered in natural language, natural language processing means for analyzing the question and extracting necessary information, sentiment analysis means for analyzing the user's emotions contained in the question, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer that takes the user's emotions into consideration based on the analysis results, and means for displaying the generated answer. As a result, the user can enter a question in natural language, quickly obtain the necessary information without requiring specialized knowledge, and be provided with an answer that is appropriate to the user's emotions.

[0740] "Means for receiving questions entered in natural language" refers to an interface for receiving text data entered by a user in natural language.

[0741] "Natural language processing means" refers to technologies for analyzing received natural language text data and extracting intent and important information.

[0742] "Emotion analysis methods" are technologies that analyze a user's emotions from natural language text data and identify their emotional state.

[0743] A "query generation method" is a technology that generates query statements (SQL queries) to be executed against a database based on the analyzed information.

[0744] "Data analysis methods" refer to techniques for analyzing data obtained from databases and extracting and calculating useful information.

[0745] "Answer generation means" refers to a technology for generating responses to users in natural language form based on analyzed data and the user's emotional state.

[0746] "Means for displaying generated answers" refers to an interface for visually displaying generated answers to the user.

[0747] This invention relates to a building management system that analyzes questions entered by users in natural language and provides appropriate answers to those questions. This system is designed to enable efficient building management even for users without specialized knowledge.

[0748] Hardware and software to use

[0749] The main hardware and software components of this system include:

[0750] Management terminal: A device that provides an interface for users to enter questions. Examples include PCs, tablets, and smartphones.

[0751] Server: The primary device responsible for parsing questions, generating queries to the database, performing data analysis, and generating answers.

[0752] Natural language processing engine: Software such as the Google Cloud Natural Language API that analyzes questions and extracts important information.

[0753] Emotion analysis engine: Software for analyzing user emotions, such as IBM Watson Tone Analyzer.

[0754] Database: A database that stores data on a building's energy consumption and carbon dioxide emissions.

[0755] Interface software: Software that retrieves questions entered by the user, sends them to the server, and receives and displays the answers from the server.

[0756] Specific operation of the system

[0757] Users input questions in natural language using a dedicated interface on the management terminal. For example, they might input a question like, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0758] The management terminal retrieves this question as text data and sends it to the server as an HTTP request. This request includes the question content and user-related identification information.

[0759] The server passes the received question to a natural language processing engine and an emotion analysis engine for analysis. The natural language processing engine understands the context of the question and extracts important information. The emotion analysis engine analyzes the user's emotions and understands the user's state.

[0760] Based on the analyzed information, the server generates a specific SQL query to execute against the database. For example, it might generate a query like "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X".

[0761] The server sends the generated query to the database and retrieves the necessary data. The retrieved data is then analyzed by data analysis tools, for example, to compare energy consumption and carbon dioxide emissions, and to calculate savings.

[0762] The server generates specific responses in natural language based on the analysis results and the user's emotional state. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[0763] The generated response is sent to the management terminal as an HTTP response. The management terminal receives this response and displays it visually to the user.

[0764] Examples of specific cases and prompt statements

[0765] As a concrete example, the following prompt statements are possible:

[0766] Question: "Have you reduced energy and carbon dioxide emissions compared to last year? How much money are you saving?"

[0767] Answer: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[0768] This invention allows users to input questions in natural language without requiring specialized knowledge of building management, and to obtain quick and appropriate answers. Furthermore, the emotion analysis engine provides answers that respond to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] User input of question

[0772] User: Use the dedicated interface on the management terminal to enter questions in natural language. For example, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0773] Input: Text data entered in natural language.

[0774] Output: The question text displayed on the interface.

[0775] Step 2:

[0776] Sending from the terminal to the server

[0777] Terminal: Retrieves the user's input as text data, generates an HTTP request, and sends it to the server.

[0778] Input: Text data of the question.

[0779] Output: HTTP request containing the question content.

[0780] Step 3:

[0781] Server receives and analyzes questions.

[0782] Server: Parses the received HTTP request and extracts the question as text. This is then passed to the natural language processing engine and sentiment analysis engine for analysis.

[0783] Server: Uses a natural language processing engine (e.g., Google Cloud Natural Language API) to understand the context of the question and extract important information.

[0784] Server: Uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to identify the user's emotions.

[0785] Input: HTTP request containing the question content.

[0786] Output: Analyzed information (keywords, context, emotional state).

[0787] Step 4:

[0788] Generating queries to the database

[0789] Server: Generates SQL queries to the database based on information obtained from the NLP engine and emotion engine. For example, queries to retrieve "last year's energy consumption" or "this year's energy consumption".

[0790] Input: Analyzed information (keywords, context, emotional state).

[0791] Output: The generated SQL query.

[0792] Step 5:

[0793] Execute queries against the database

[0794] Server: Uses the generated SQL query to query the database and retrieve the necessary data.

[0795] Server: Establishes a database connection and executes queries while handling errors.

[0796] Input: SQL query.

[0797] Output: Data retrieved from the database.

[0798] Step 6:

[0799] Data Analysis

[0800] Server: Analyzes data obtained from the database to compare energy consumption and carbon dioxide emissions, and calculate savings.

[0801] Server: Performs calculations and calculates the difference and savings.

[0802] Input: Data retrieved from a database.

[0803] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved).

[0804] Step 7:

[0805] Answer generation

[0806] Server: Based on the analysis results and the user's emotional state, it generates specific responses in natural language. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions have decreased by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[0807] Input: Analysis results, user's emotional state.

[0808] Output: Generated answer text.

[0809] Step 8:

[0810] Sending responses from the server to the terminal.

[0811] Server: Sends the generated response text to the management terminal as an HTTP response.

[0812] Server: Formats the response into JSON format or similar and generates an HTTP response.

[0813] Input: Generated response text.

[0814] Output: HTTP response.

[0815] Step 9:

[0816] Displaying responses via device

[0817] Terminal: Analyzes the HTTP response received from the server and displays it to the user in a visually easy-to-understand format. For example, it might display: "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen."

[0818] Input: HTTP response.

[0819] Output: The answer text displayed on the terminal.

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0822] Traditional building management systems made it difficult for users without specialized knowledge to effectively utilize the system. Furthermore, the lack of means to provide quick and appropriate answers to user questions hindered the user experience. This made it particularly difficult to obtain information regarding energy management and production efficiency, impeding the efficiency of management operations. Additionally, the failure to consider user emotions in response generation resulted in low user satisfaction.

[0823] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving a question input in natural language, natural language processing means for analyzing the question and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer based on the analysis results, means for displaying the generated answer, and sentiment analysis means for analyzing the user's emotions. As a result, the user can quickly obtain specific information regarding energy management and production efficiency through questions in natural language without specialized knowledge. In addition, the user experience is improved because appropriate answers are provided based on the user's emotions.

[0824] "Natural language" refers to the language that humans use on a daily basis, and is a means of conveying information in the form of writing and conversation.

[0825] "Natural language processing means" refers to technologies for analyzing natural language, such as questions and commands, and extracting necessary information.

[0826] A "query generation method" is a means of generating a query for a database based on the extracted information.

[0827] "Data analysis methods" refer to techniques for analyzing data obtained from databases to derive useful information and trends.

[0828] A "response generation method" is a means of generating responses for users based on the results of data analysis.

[0829] "Display means" refers to a means of displaying the generated response so that the user can confirm it.

[0830] An "emotion analysis tool" is a means of analyzing the user's emotions contained in questions and commands, and enabling responses that correspond to those emotions.

[0831] "Energy consumption" refers to the total amount of energy consumed within a certain period.

[0832] "Carbon dioxide emissions" refers to the total amount of carbon dioxide emitted within a certain period.

[0833] "Production efficiency" is an indicator that represents the efficiency of production results in relation to the resources invested in a factory or production line.

[0834] A "factory management system" is a system that comprehensively handles the information necessary for the operation and management of a factory, and supports efficient operations.

[0835] This invention relates to a building management system that analyzes questions entered in natural language, retrieves necessary information from a database, analyzes it, generates answers, and takes user emotions into consideration. Specific embodiments for carrying out this invention are described below.

[0836] The system primarily uses the following hardware and software:

[0837] Server (question analysis and data processing)

[0838] Smartphone (user device)

[0839] Database server (data storage)

[0840] The specific software used includes the following:

[0841] Natural Language Processing Engine (NLPEngine)

[0842] Sentiment Engine

[0843] Database connection library (MySQL Connector)

[0844] The user inputs a question in natural language from their smartphone. For example, they might input, "How much did this month's energy consumption increase compared to last month, and what was the reason?" The smartphone receives the question and sends it to the server as an HTTP request. Upon receiving the question, the server automatically uses NLPEngine to analyze the context of the question. NLPEngine performs tokenization and morphological analysis to extract the necessary information from the question.

[0845] Next, the server uses a SentimentEngine to analyze the user's emotions. This identifies the emotional elements contained in the question. Based on the analyzed information, an SQL query is generated for the database. The generated query is sent to the database server, and the necessary data is retrieved.

[0846] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. For example, it can determine how much energy consumption has increased compared to the previous month, and whether the cause is the introduction of a new production line.

[0847] Based on the analysis results, the response generation system generates an appropriate response for the user. Using an emotion analysis engine, the response is adjusted to a tone that matches the user's emotions. For example, "This month's energy consumption has increased by 10% compared to last month. The main reason is the introduction of a new production line."

[0848] The generated response is sent from the server to the user's smartphone as an HTTP response. The smartphone then displays the received response to the user. This allows users, even without specialized knowledge, to quickly obtain information on energy management and production efficiency using natural language and utilize it in their management activities.

[0849] As a concrete example, when the question "How much did this month's energy consumption increase compared to last month, and what was the reason?" is entered, the system, after going through the aforementioned analysis flow, generates the answer "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." Based on the same question, the AI ​​model can be given example prompts such as "Please tell me the reason for the fluctuation in the factory's energy consumption" and "What caused the increase in energy consumption compared to last month?"

[0850] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0851] Step 1:

[0852] The user enters a question from their smartphone. For example, they might enter, "How much did this month's energy consumption increase compared to last month, and what was the reason?" In this case, the smartphone receives the question in natural language as input and displays the question on the smartphone as output.

[0853] Step 2:

[0854] The device (smartphone) sends the received question to the server as an HTTP request. This request includes the question content and user-specific information. It receives a request containing a natural language question and user information as input, and sends that request to the server as output.

[0855] Step 3:

[0856] The server receives an HTTP request and uses a natural language processing engine (NLPEngine) to analyze the context of the question. Specifically, it tokenizes the natural language question received as input, performs morphological analysis, and understands the context of the question. As a result, the necessary information is extracted, and the extracted information is obtained as output.

[0857] Step 4:

[0858] The server uses a SentimentEngine to analyze the user's emotions. Based on the questions received as input, emotion analysis is performed, and the user's emotional state is identified. The user's emotion data is obtained as output.

[0859] Step 5:

[0860] The server generates an SQL query to the database based on the extracted information and sentiment data. It takes the extracted information and sentiment data as input and outputs the generated SQL query. For example, a query like "SELECT energy_last_month, energy_this_month, reason FROM factory_energy_data WHERE factory_id = X;" is generated.

[0861] Step 6:

[0862] The server sends the generated SQL query to the database server and retrieves the necessary data. It receives the generated SQL query as input and queries the database server. The retrieved data is obtained as output.

[0863] Step 7:

[0864] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. It receives acquired data as input and performs data analysis such as calculating fluctuations in energy consumption and savings. The analysis results are obtained as output.

[0865] Step 8:

[0866] The server generates responses based on analysis results and user sentiment data. It receives analysis results and sentiment data as input and adjusts the response to match the user's sentiment. For example, it might generate a response such as, "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." The generated response is obtained as output.

[0867] Step 9:

[0868] The server sends the generated response to the user's smartphone as an HTTP response. It receives the generated response as input and sends that response to the smartphone as output.

[0869] Step 10:

[0870] The device (smartphone) displays the received response to the user. It receives the response as input and displays that response on the smartphone screen as output. This allows the user to obtain a specific answer to the question.

[0871] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0872] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0873] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0874] [Third Embodiment]

[0875] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0876] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0877] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0878] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0879] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0880] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0881] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0882] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0883] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0884] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0885] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0886] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0887] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0888] System Processing Overview

[0889] 1. User input of question

[0890] Users enter questions through a dedicated interface on the management terminal. For example, a possible format might be, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0891] 2. Sending from the terminal to the server

[0892] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[0893] 3. Server receives and analyzes the query.

[0894] The server passes the received question to a natural language processing (NLP) engine for analysis. For example, tokenization and morphological analysis are performed to understand the context of the question and extract the necessary information.

[0895] 4. Generating queries to the database

[0896] The server generates specific SQL queries for the database based on the information extracted by the NLP engine. For example, queries related to "last year's energy consumption" and "this year's energy consumption" are generated.

[0897] 5. Execute queries on the database

[0898] The server uses the generated SQL query to query the database. The database returns the necessary data.

[0899] 6. Data Analysis

[0900] The server analyzes the acquired data to obtain specific answers to the user's questions. For example, it calculates the difference in energy consumption and carbon dioxide emissions to determine the amount of savings.

[0901] 7. Generating the answer

[0902] The server generates responses in a user-friendly format based on the analysis results. For example, it might generate a response such as, "Energy consumption decreased by 10% compared to last year, resulting in savings of approximately 1 million yen."

[0903] 8. Sending responses from the server to the terminal.

[0904] The response generated by the server is sent to the user's management terminal as an HTTP response.

[0905] 9. Displaying responses via the device

[0906] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[0907] Specific example

[0908] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0909] 1. The user enters the question from the management terminal.

[0910] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[0911] 2. The terminal receives user input and sends it to the server.

[0912] 3. The server receives the question and analyzes it using the NLP engine.

[0913] 4. The server generates an SQL query based on the analysis results.

[0914] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0915] 5. The server sends a query to the database and retrieves the necessary data.

[0916] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0917] 7. The server generates an answer based on the analysis results.

[0918] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0919] 8. The server sends the generated response to the terminal.

[0920] 9. The device displays the received response.

[0921] This invention allows users to easily input questions in natural language and quickly obtain the necessary information, even without specialized knowledge. This system can significantly improve the efficiency of building management.

[0922] The following describes the processing flow.

[0923] Step 1:

[0924] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[0925] Step 2:

[0926] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[0927] Step 3:

[0928] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[0929] Step 4:

[0930] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[0931] Step 5:

[0932] The server generates the necessary database queries based on the analysis results of the NLP engine. For example, it generates queries related to "last year's energy consumption" and "this year's energy consumption."

[0933] Step 6:

[0934] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[0935] Step 7:

[0936] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[0937] Step 8:

[0938] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[0939] Step 9:

[0940] The server generates a response based on the analysis results. For example, it might create a specific response such as, "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[0941] Step 10:

[0942] The server sends the generated response to the terminal as an HTTP response.

[0943] Step 11:

[0944] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[0945] (Example 1)

[0946] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0947] In modern building management, there is a demand for efficient management even for non-experts. However, current systems are difficult for users without specialized knowledge to operate, making it difficult to obtain information quickly and accurately. Furthermore, advanced technology is required to extract and analyze necessary information from vast amounts of data. Solving these problems is essential.

[0948] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0949] In this invention, the server includes means for receiving questions entered in natural language, natural language processing means for analyzing the questions and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for users to easily input questions in natural language and quickly and accurately obtain the necessary information, even without specialized knowledge.

[0950] "Natural language" refers to the language system that humans use on a daily basis, and is expressed through sound or writing.

[0951] "Means for receiving questions entered in natural language" refers to devices or software that receive questions entered by users in natural language and incorporate them into the system.

[0952] "Natural language processing means" refers to technologies and algorithms that analyze input natural language text, understand its context and meaning, and extract necessary information.

[0953] "Query generation means" refers to devices or software that generate query commands for a database based on analyzed information.

[0954] "Data analysis means" refers to processing devices or software used to analyze data obtained from a database and derive answers to user questions.

[0955] "Answer generation means" refers to devices or software that generate answers for the user based on analysis results.

[0956] "Means of display" refers to devices or software that display the generated answers in a way that users can verify.

[0957] "Tokenization" refers to the process of dividing natural language text into smaller units such as words and phrases.

[0958] Morphological analysis refers to the process of breaking down words into smaller parts and analyzing their basic forms in order to understand the meaning and role of each word that makes up a natural language text.

[0959] A "database" refers to a system for storing, efficiently managing, and retrieving collections of data.

[0960] "Energy consumption" refers to the amount of energy used over a specific period.

[0961] "Carbon dioxide emissions" refers to the amount of carbon dioxide emitted during a specific period.

[0962] "Difference" refers to the difference in quantity or numerical value between two things being compared.

[0963] "Savings" refers to the amount of money reduced by a particular action or measure.

[0964] An "HTTP request" is a protocol used by web browsers and other clients to request data from a server.

[0965] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[0966] System Configuration

[0967] This invention comprises the following main components:

[0968] 1. Means for receiving questions entered in natural language.

[0969] The terminal receives questions entered by the user through a dedicated interface. These questions are in natural language and do not require any special formatting. For example, it accepts questions such as, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0970] 2. Natural Language Processing Means

[0971] The server passes the received question to a natural language processing (NLP) engine for analysis. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize and morphologically analyze the question, understand its context, and extract the necessary information.

[0972] 3. Query generation means

[0973] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." Specifically, it generates an SQL statement like this: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[0974] 4. Data Analysis Methods

[0975] The server uses the generated SQL query to query the database and retrieve the necessary data. Next, it analyzes that data, compares energy consumption and carbon dioxide emissions, and calculates the amount of savings.

[0976] 5. Answer generation means

[0977] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[0978] 6. Means for displaying the generated response

[0979] The device displays the received responses to the user. This allows the user to easily obtain specific answers to their questions.

[0980] Specific example

[0981] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[0982] 1. The user enters the question from the management terminal.

[0983] "Have you reduced energy and carbon emissions compared to last year? How much money are you saving?"

[0984] 2. The terminal receives user input and sends it to the server.

[0985] 3. The server receives the question and analyzes it using an NLP engine. For example, it uses libraries such as spaCy or NLTK to perform tokenization and morphological analysis to understand the question.

[0986] 4. The server generates an SQL query based on the analysis results.

[0987] "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[0988] 5. The server sends queries to the database and retrieves the necessary data. A database management system such as MySQL or PostgreSQL is used.

[0989] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[0990] 7. The server generates an answer based on the analysis results.

[0991] "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[0992] 8. The server sends the generated response to the terminal.

[0993] 9. The device displays the received response to the user.

[0994] This allows users to easily input questions in natural language, even without specialized knowledge, and quickly and accurately obtain the information they need.

[0995] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0996] Step 1: User enters question

[0997] Users enter questions in natural language using a dedicated interface on the management terminal. These questions do not require a special format as they are subject to natural language processing. For example, they might enter something like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[0998] Input: Question in natural language format

[0999] Output: Data containing the question content

[1000] Step 2: Sending from the terminal to the server

[1001] The terminal receives the question entered by the user and sends it to the server as an HTTP request. This request contains the question and information related to the user.

[1002] Input: Data containing the question content

[1003] Output: HTTP request containing the question data

[1004] Step 3: Server receives and analyzes the question.

[1005] The server parses the received HTTP request and extracts the question content. Next, it passes the question to a natural language processing (NLP) engine for analysis. For example, it might tokenize the question using libraries such as spaCy or NLTK and then perform morphological analysis to understand the context.

[1006] Input: HTTP request (contains the question)

[1007] Output: Tokenized and morphologically analyzed question data

[1008] Step 4: Generate queries to the database

[1009] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." The specific SQL statements are as follows:

[1010] Example: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[1011] Input: Tokenized and morphologically analyzed question data

[1012] Output: SQL query against the database

[1013] Step 5: Execute queries on the database

[1014] The server sends the generated SQL query to the database and retrieves the necessary data. The database management system used is typically MySQL or PostgreSQL.

[1015] Input: SQL query

[1016] Output: Data retrieved from the database

[1017] Step 6: Data Analysis

[1018] The server analyzes the acquired data. Specifically, it compares energy consumption and carbon dioxide emissions from last year and this year, and calculates the amount of savings from the difference. This allows it to provide specific answers to user questions.

[1019] Input: Data retrieved from the database

[1020] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved)

[1021] Step 7: Generating the answer

[1022] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response like, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[1023] Input: Analysis results

[1024] Output: Generated answer

[1025] Step 8: Sending the response from the server to the terminal

[1026] The server sends the generated response to the terminal as an HTTP response.

[1027] Input: Generated answer

[1028] Output: HTTP response (response content)

[1029] Step 9: Displaying the response via the device

[1030] The terminal displays the received response on the user interface. This allows the user to easily obtain specific answers to their questions.

[1031] Input: HTTP response (response content)

[1032] Output: Answer displayed in the user interface

[1033] In this way, users can easily input questions in natural language without needing specialized knowledge, and quickly and accurately obtain the necessary information.

[1034] (Application Example 1)

[1035] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1036] In factory management, it is crucial for managers and workers to understand operating conditions and equipment status in real time. However, conventional systems require specialized knowledge, and data collection and analysis are time-consuming. Furthermore, the inability to easily ask and answer questions via voice input hinders efficient management. To solve these problems, a system is needed that accepts questions in natural language and provides quick and accurate answers.

[1037] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1038] In this invention, the server includes means for receiving questions input by voice, voice recognition means for converting the questions into text, natural language processing means for analyzing the text and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for managers and workers to query the operating status of the factory and the status of equipment in real time using voice and obtain answers quickly and accurately.

[1039] "Means for receiving questions entered via voice" refers to a function that recognizes machine speech and captures that voice data.

[1040] "Speech recognition means" refers to a technology that analyzes received speech data and converts it into corresponding text.

[1041] "Natural language processing tools" are functions that analyze text-based questions, understand their context and content, and extract necessary information.

[1042] A "query generation method" is a technology that generates request statements, such as SQL queries, for querying a database based on information extracted through natural language processing.

[1043] A "data analysis tool" is a function that analyzes data obtained from a database and derives appropriate answers to questions.

[1044] "Answer generation method" refers to a technology that creates answers in a user-friendly format based on data analysis results.

[1045] "Means of display" refers to display devices or display software that provide the generated answers to the user visually.

[1046] This invention is a system for factory management that accepts questions using voice and provides answers in real time. This system enables factory managers and workers to efficiently understand the operating status and equipment status of the factory through voice.

[1047] The main components of this system include speech recognition software, a natural language processing engine, a database management system, and smart glasses. Specifically, it uses the following hardware and software:

[1048] Hardware to use

[1049] Smart glasses: Receiving and displaying voice input

[1050] Server: Data processing and database management

[1051] Software to use

[1052] Speech recognition software (e.g., Google Cloud Speech-to-Text): Converts speech to text.

[1053] Natural language processing engines (e.g., SpaCy and NLTK): Question analysis

[1054] Database management system (e.g., MySQL): for storing data and executing queries.

[1055] The specific process of the system is as follows:

[1056] Voice input

[1057] Workers and managers input questions by voice into smart glasses. For example, questions could include, "How many machine malfunctions have there been this week?" or "What is the current energy consumption?"

[1058] Speech recognition

[1059] The smart glasses convert the input audio into text using speech recognition software and send that text data to a server.

[1060] question analysis

[1061] The server analyzes the received text data using a natural language processing engine to understand the context and content of the question and extract the necessary information. For example, it performs tokenization and morphological analysis to obtain specific information for querying the database.

[1062] Query generation and data retrieval

[1063] Based on the analysis results, an SQL query is generated for the database. The server uses this query to retrieve the necessary data from the database.

[1064] Data analysis and response generation

[1065] The server analyzes the data obtained from the database and generates specific answers to the questions. For example, it might generate an answer such as, "There have been 3 machine failures this week, and the current energy consumption is 1000kWh."

[1066] Display the answer

[1067] The generated response is sent from the server to the smart glasses and displayed on the screen.

[1068] Specific example

[1069] When an administrator asks, "Please tell me the machine's operating hours for this month," the system processes the request using the following steps:

[1070] 1. Recognize speech and convert it to text.

[1071] 2. Analyze the relevant text using natural language processing.

[1072] 3. Send a query to the database and retrieve the necessary data.

[1073] 4. Analyze the obtained data and generate the answer.

[1074] 5. Display the answer on smart glasses.

[1075] Example of a prompt

[1076] "I'd like to know the operating hours for each machine this month."

[1077] "Please tell me the number of malfunctions that occurred this month."

[1078] As a result, this system allows managers and workers to efficiently perform factory management tasks.

[1079] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1080] Step 1:

[1081] The user inputs a question by voice into the smart glasses. For example, they might say, "How many machine failures were there this week?" At this point, the input is the user's voice.

[1082] Step 2:

[1083] Smart glasses use speech recognition software (e.g., Google Cloud Speech-to-Text) to convert speech to text. They analyze the speech data and generate corresponding text data. The output is the corresponding text data.

[1084] Step 3:

[1085] The terminal sends the generated text data to the server as an HTTP request. The input is text data, and the output is an HTTP request.

[1086] Step 4:

[1087] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). Specifically, it performs tokenization and morphological analysis to extract the context and keywords of the question. The input is text data, and the output is the extracted keywords and contextual information.

[1088] Step 5:

[1089] The server generates an SQL query to query the database based on the extracted information. For example, a query like "SELECT COUNT() FROM malfunction_logs WHERE week = 'current_week';" is generated. The input is the extracted information, and the output is the generated SQL query.

[1090] Step 6:

[1091] The server sends the generated SQL query to the database management system (e.g., MySQL) and retrieves the necessary data. The input is the SQL query, and the output is the data returned from the database.

[1092] Step 7:

[1093] The server analyzes the acquired data using data analysis tools and generates specific answers to questions. For example, it might generate an answer such as, "There were 3 machine failures this week." The input is data obtained from the database, and the output is the generated answer.

[1094] Step 8:

[1095] The server sends the generated response to the smart glasses as an HTTP response. The input is the generated response, and the output is the HTTP response.

[1096] Step 9:

[1097] The smart glasses display the received response as text data on the screen. The input is the response as an HTTP response, and the output is the text displayed on the screen.

[1098] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1099] This invention relates to a building management system that analyzes questions entered in natural language and the user's emotions, acquires and analyzes necessary data, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[1100] System Processing Overview

[1101] 1. User input of question

[1102] Users enter questions through a dedicated interface on the management terminal. For example, they might enter a question like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[1103] 2. Sending from the terminal to the server

[1104] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[1105] 3. Server receives and analyzes the query.

[1106] The server passes the received question to a natural language processing (NLP) engine and an emotion engine for analysis. The NLP engine understands the context of the question and extracts the necessary information. The emotion engine recognizes the user's emotions as expressed in the question.

[1107] 4. Generating queries to the database

[1108] The server generates specific SQL queries for the database based on the information extracted by the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[1109] 5. Execute queries on the database

[1110] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[1111] 6. Data Analysis

[1112] The server analyzes the acquired data to obtain specific analysis results regarding the user's questions and emotions. This includes comparisons of differences in energy consumption and carbon dioxide emissions.

[1113] 7. Generating the answer

[1114] The server generates responses based on analysis results and the user's emotional state. For example, it might create a specific response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen." The emotion engine adjusts the tone and expression of the response according to the user's emotions.

[1115] 8. Sending responses from the server to the terminal.

[1116] The response generated by the server is sent to the user's management terminal as an HTTP response.

[1117] 9. Displaying responses via the device

[1118] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[1119] Specific example

[1120] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[1121] 1. The user enters the question from the management terminal.

[1122] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[1123] 2. The terminal receives user input and sends it to the server.

[1124] 3. The server receives the question and analyzes it using the NLP engine and the emotion engine.

[1125] The NLP engine understands the context and extracts the necessary information. The emotion engine recognizes the user's emotions.

[1126] 4. The server generates an SQL query based on the analysis results.

[1127] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[1128] 5. The server sends a query to the database and retrieves the necessary data.

[1129] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[1130] 7. The server generates a response based on the analysis results and the user's emotional state.

[1131] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[1132] 8. The server sends the generated response to the terminal.

[1133] 9. The device displays the received response.

[1134] This invention allows users to easily input questions in natural language and quickly obtain necessary information, even without specialized knowledge. Furthermore, the emotion engine provides responses tailored to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[1135] The following describes the processing flow.

[1136] Step 1:

[1137] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1138] Step 2:

[1139] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[1140] Step 3:

[1141] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[1142] Step 4:

[1143] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[1144] Step 5:

[1145] The server's sentiment engine analyzes the user's emotional elements contained in the question. This allows the server to understand the user's emotional state at the time the question was asked.

[1146] Step 6:

[1147] The server generates the necessary database queries based on the analysis results of the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[1148] Step 7:

[1149] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[1150] Step 8:

[1151] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[1152] Step 9:

[1153] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[1154] Step 10:

[1155] The server generates a response based on the analysis results. In this process, it uses the results of the emotion engine to generate a response with a tone and language appropriate to the user's emotional state. For example, it might create a specific and considerate response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen."

[1156] Step 11:

[1157] The server sends the generated response to the terminal as an HTTP response.

[1158] Step 12:

[1159] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[1160] (Example 2)

[1161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1162] In building management, there is a need for a means that allows users to efficiently and effectively acquire and manage information without requiring specialized knowledge. However, conventional systems require complex operations and specialized knowledge, which can hinder daily operations. Furthermore, providing quick responses that take user emotions into consideration is difficult, and improving the user experience is also a challenge.

[1163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1164] In this invention, the server includes means for receiving a question entered in natural language, natural language processing means for analyzing the question and extracting necessary information, sentiment analysis means for analyzing the user's emotions contained in the question, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer that takes the user's emotions into consideration based on the analysis results, and means for displaying the generated answer. As a result, the user can enter a question in natural language, quickly obtain the necessary information without requiring specialized knowledge, and be provided with an answer that is appropriate to the user's emotions.

[1165] "Means for receiving questions entered in natural language" refers to an interface for receiving text data entered by a user in natural language.

[1166] "Natural language processing means" refers to technologies for analyzing received natural language text data and extracting intent and important information.

[1167] "Emotion analysis methods" are technologies that analyze a user's emotions from natural language text data and identify their emotional state.

[1168] A "query generation method" is a technology that generates query statements (SQL queries) to be executed against a database based on the analyzed information.

[1169] "Data analysis methods" refer to techniques for analyzing data obtained from databases and extracting and calculating useful information.

[1170] "Answer generation means" refers to a technology for generating responses to users in natural language form based on analyzed data and the user's emotional state.

[1171] "Means for displaying generated answers" refers to an interface for visually displaying generated answers to the user.

[1172] This invention relates to a building management system that analyzes questions entered by users in natural language and provides appropriate answers to those questions. This system is designed to enable efficient building management even for users without specialized knowledge.

[1173] Hardware and software to use

[1174] The main hardware and software components of this system include:

[1175] Management terminal: A device that provides an interface for users to enter questions. Examples include PCs, tablets, and smartphones.

[1176] Server: The primary device responsible for parsing questions, generating queries to the database, performing data analysis, and generating answers.

[1177] Natural language processing engine: Software such as the Google Cloud Natural Language API that analyzes questions and extracts important information.

[1178] Emotion analysis engine: Software for analyzing user emotions, such as IBM Watson Tone Analyzer.

[1179] Database: A database that stores data on a building's energy consumption and carbon dioxide emissions.

[1180] Interface software: Software that retrieves questions entered by the user, sends them to the server, and receives and displays the answers from the server.

[1181] Specific operation of the system

[1182] Users input questions in natural language using a dedicated interface on the management terminal. For example, they might input a question like, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1183] The management terminal retrieves this question as text data and sends it to the server as an HTTP request. This request includes the question content and user-related identification information.

[1184] The server passes the received question to a natural language processing engine and an emotion analysis engine for analysis. The natural language processing engine understands the context of the question and extracts important information. The emotion analysis engine analyzes the user's emotions and understands the user's state.

[1185] Based on the analyzed information, the server generates a specific SQL query to execute against the database. For example, it might generate a query like "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X".

[1186] The server sends the generated query to the database and retrieves the necessary data. The retrieved data is then analyzed by data analysis tools, for example, to compare energy consumption and carbon dioxide emissions, and to calculate savings.

[1187] The server generates specific responses in natural language based on the analysis results and the user's emotional state. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[1188] The generated response is sent to the management terminal as an HTTP response. The management terminal receives this response and displays it visually to the user.

[1189] Examples of specific cases and prompt statements

[1190] As a concrete example, the following prompt statements are possible:

[1191] Question: "Have you reduced energy and carbon dioxide emissions compared to last year? How much money are you saving?"

[1192] Answer: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[1193] This invention allows users to input questions in natural language without requiring specialized knowledge of building management, and to obtain quick and appropriate answers. Furthermore, the emotion analysis engine provides answers that respond to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[1194] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1195] Step 1:

[1196] User input of question

[1197] User: Use the dedicated interface on the management terminal to enter questions in natural language. For example, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1198] Input: Text data entered in natural language.

[1199] Output: The question text displayed on the interface.

[1200] Step 2:

[1201] Sending from the terminal to the server

[1202] Terminal: Retrieves the user's input as text data, generates an HTTP request, and sends it to the server.

[1203] Input: Text data of the question.

[1204] Output: HTTP request containing the question content.

[1205] Step 3:

[1206] Server receives and analyzes questions.

[1207] Server: Parses the received HTTP request and extracts the question as text. This is then passed to the natural language processing engine and sentiment analysis engine for analysis.

[1208] Server: Uses a natural language processing engine (e.g., Google Cloud Natural Language API) to understand the context of the question and extract important information.

[1209] Server: Uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to identify the user's emotions.

[1210] Input: HTTP request containing the question content.

[1211] Output: Analyzed information (keywords, context, emotional state).

[1212] Step 4:

[1213] Generating queries to the database

[1214] Server: Generates SQL queries to the database based on information obtained from the NLP engine and emotion engine. For example, queries to retrieve "last year's energy consumption" or "this year's energy consumption".

[1215] Input: Analyzed information (keywords, context, emotional state).

[1216] Output: The generated SQL query.

[1217] Step 5:

[1218] Execute queries against the database

[1219] Server: Uses the generated SQL query to query the database and retrieve the necessary data.

[1220] Server: Establishes a database connection and executes queries while handling errors.

[1221] Input: SQL query.

[1222] Output: Data retrieved from the database.

[1223] Step 6:

[1224] Data Analysis

[1225] Server: Analyzes data obtained from the database to compare energy consumption and carbon dioxide emissions, and calculate savings.

[1226] Server: Performs calculations and calculates the difference and savings.

[1227] Input: Data retrieved from a database.

[1228] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved).

[1229] Step 7:

[1230] Answer generation

[1231] Server: Based on the analysis results and the user's emotional state, it generates specific responses in natural language. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions have decreased by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[1232] Input: Analysis results, user's emotional state.

[1233] Output: Generated answer text.

[1234] Step 8:

[1235] Sending responses from the server to the terminal.

[1236] Server: Sends the generated response text to the management terminal as an HTTP response.

[1237] Server: Formats the response into JSON format or similar and generates an HTTP response.

[1238] Input: Generated response text.

[1239] Output: HTTP response.

[1240] Step 9:

[1241] Displaying responses via device

[1242] Terminal: Analyzes the HTTP response received from the server and displays it to the user in a visually easy-to-understand format. For example, it might display: "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen."

[1243] Input: HTTP response.

[1244] Output: The answer text displayed on the terminal.

[1245] (Application Example 2)

[1246] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1247] Traditional building management systems made it difficult for users without specialized knowledge to effectively utilize the system. Furthermore, the lack of means to provide quick and appropriate answers to user questions hindered the user experience. This made it particularly difficult to obtain information regarding energy management and production efficiency, impeding the efficiency of management operations. Additionally, the failure to consider user emotions in response generation resulted in low user satisfaction.

[1248] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving a question input in natural language, natural language processing means for analyzing the question and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer based on the analysis results, means for displaying the generated answer, and sentiment analysis means for analyzing the user's emotions. As a result, the user can quickly obtain specific information regarding energy management and production efficiency through questions in natural language without specialized knowledge. In addition, the user experience is improved because appropriate answers are provided based on the user's emotions.

[1249] "Natural language" refers to the language that humans use on a daily basis, and is a means of conveying information in the form of writing and conversation.

[1250] "Natural language processing means" refers to technologies for analyzing natural language, such as questions and commands, and extracting necessary information.

[1251] A "query generation method" is a means of generating a query for a database based on the extracted information.

[1252] "Data analysis methods" refer to techniques for analyzing data obtained from databases to derive useful information and trends.

[1253] A "response generation method" is a means of generating responses for users based on the results of data analysis.

[1254] "Display means" refers to a means of displaying the generated response so that the user can confirm it.

[1255] An "emotion analysis tool" is a means of analyzing the user's emotions contained in questions and commands, and enabling responses that correspond to those emotions.

[1256] "Energy consumption" refers to the total amount of energy consumed within a certain period.

[1257] "Carbon dioxide emissions" refers to the total amount of carbon dioxide emitted within a certain period.

[1258] "Production efficiency" is an indicator that represents the efficiency of production results in relation to the resources invested in a factory or production line.

[1259] A "factory management system" is a system that comprehensively handles the information necessary for the operation and management of a factory, and supports efficient operations.

[1260] This invention relates to a building management system that analyzes questions entered in natural language, retrieves necessary information from a database, analyzes it, generates answers, and takes user emotions into consideration. Specific embodiments for carrying out this invention are described below.

[1261] The system primarily uses the following hardware and software:

[1262] Server (question analysis and data processing)

[1263] Smartphone (user device)

[1264] Database server (data storage)

[1265] The specific software used includes the following:

[1266] Natural Language Processing Engine (NLPEngine)

[1267] Sentiment Engine

[1268] Database connection library (MySQL Connector)

[1269] The user inputs a question in natural language from their smartphone. For example, they might input, "How much did this month's energy consumption increase compared to last month, and what was the reason?" The smartphone receives the question and sends it to the server as an HTTP request. Upon receiving the question, the server automatically uses NLPEngine to analyze the context of the question. NLPEngine performs tokenization and morphological analysis to extract the necessary information from the question.

[1270] Next, the server uses a SentimentEngine to analyze the user's emotions. This identifies the emotional elements contained in the question. Based on the analyzed information, an SQL query is generated for the database. The generated query is sent to the database server, and the necessary data is retrieved.

[1271] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. For example, it can determine how much energy consumption has increased compared to the previous month, and whether the cause is the introduction of a new production line.

[1272] Based on the analysis results, the response generation system generates an appropriate response for the user. Using an emotion analysis engine, the response is adjusted to a tone that matches the user's emotions. For example, "This month's energy consumption has increased by 10% compared to last month. The main reason is the introduction of a new production line."

[1273] The generated response is sent from the server to the user's smartphone as an HTTP response. The smartphone then displays the received response to the user. This allows users, even without specialized knowledge, to quickly obtain information on energy management and production efficiency using natural language and utilize it in their management activities.

[1274] As a concrete example, when the question "How much did this month's energy consumption increase compared to last month, and what was the reason?" is entered, the system, after going through the aforementioned analysis flow, generates the answer "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." Based on the same question, the AI ​​model can be given example prompts such as "Please tell me the reason for the fluctuation in the factory's energy consumption" and "What caused the increase in energy consumption compared to last month?"

[1275] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1276] Step 1:

[1277] The user enters a question from their smartphone. For example, they might enter, "How much did this month's energy consumption increase compared to last month, and what was the reason?" In this case, the smartphone receives the question in natural language as input and displays the question on the smartphone as output.

[1278] Step 2:

[1279] The device (smartphone) sends the received question to the server as an HTTP request. This request includes the question content and user-specific information. It receives a request containing a natural language question and user information as input, and sends that request to the server as output.

[1280] Step 3:

[1281] The server receives an HTTP request and uses a natural language processing engine (NLPEngine) to analyze the context of the question. Specifically, it tokenizes the natural language question received as input, performs morphological analysis, and understands the context of the question. As a result, the necessary information is extracted, and the extracted information is obtained as output.

[1282] Step 4:

[1283] The server uses a SentimentEngine to analyze the user's emotions. Based on the questions received as input, emotion analysis is performed, and the user's emotional state is identified. The user's emotion data is obtained as output.

[1284] Step 5:

[1285] The server generates an SQL query to the database based on the extracted information and sentiment data. It takes the extracted information and sentiment data as input and outputs the generated SQL query. For example, a query like "SELECT energy_last_month, energy_this_month, reason FROM factory_energy_data WHERE factory_id = X;" is generated.

[1286] Step 6:

[1287] The server sends the generated SQL query to the database server and retrieves the necessary data. It receives the generated SQL query as input and queries the database server. The retrieved data is obtained as output.

[1288] Step 7:

[1289] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. It receives acquired data as input and performs data analysis such as calculating fluctuations in energy consumption and savings. The analysis results are obtained as output.

[1290] Step 8:

[1291] The server generates responses based on analysis results and user sentiment data. It receives analysis results and sentiment data as input and adjusts the response to match the user's sentiment. For example, it might generate a response such as, "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." The generated response is obtained as output.

[1292] Step 9:

[1293] The server sends the generated response to the user's smartphone as an HTTP response. It receives the generated response as input and sends that response to the smartphone as output.

[1294] Step 10:

[1295] The device (smartphone) displays the received response to the user. It receives the response as input and displays that response on the smartphone screen as output. This allows the user to obtain a specific answer to the question.

[1296] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1297] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1298] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1299] [Fourth Embodiment]

[1300] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1301] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1302] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1303] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1304] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1305] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1306] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1307] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1308] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1309] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1310] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1311] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1312] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1313] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[1314] System Processing Overview

[1315] 1. User input of question

[1316] Users enter questions through a dedicated interface on the management terminal. For example, a possible format might be, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1317] 2. Sending from the terminal to the server

[1318] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[1319] 3. Server receives and analyzes the query.

[1320] The server passes the received question to a natural language processing (NLP) engine for analysis. For example, tokenization and morphological analysis are performed to understand the context of the question and extract the necessary information.

[1321] 4. Generating queries to the database

[1322] The server generates specific SQL queries for the database based on the information extracted by the NLP engine. For example, queries related to "last year's energy consumption" and "this year's energy consumption" are generated.

[1323] 5. Execute queries on the database

[1324] The server uses the generated SQL query to query the database. The database returns the necessary data.

[1325] 6. Data Analysis

[1326] The server analyzes the acquired data to obtain specific answers to the user's questions. For example, it calculates the difference in energy consumption and carbon dioxide emissions to determine the amount of savings.

[1327] 7. Generating the answer

[1328] The server generates responses in a user-friendly format based on the analysis results. For example, it might generate a response such as, "Energy consumption decreased by 10% compared to last year, resulting in savings of approximately 1 million yen."

[1329] 8. Sending responses from the server to the terminal.

[1330] The response generated by the server is sent to the user's management terminal as an HTTP response.

[1331] 9. Displaying responses via the device

[1332] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[1333] Specific example

[1334] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[1335] 1. The user enters the question from the management terminal.

[1336] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[1337] 2. The terminal receives user input and sends it to the server.

[1338] 3. The server receives the question and analyzes it using the NLP engine.

[1339] 4. The server generates an SQL query based on the analysis results.

[1340] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[1341] 5. The server sends a query to the database and retrieves the necessary data.

[1342] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[1343] 7. The server generates an answer based on the analysis results.

[1344] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[1345] 8. The server sends the generated response to the terminal.

[1346] 9. The device displays the received response.

[1347] This invention allows users to easily input questions in natural language and quickly obtain the necessary information, even without specialized knowledge. This system can significantly improve the efficiency of building management.

[1348] The following describes the processing flow.

[1349] Step 1:

[1350] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1351] Step 2:

[1352] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[1353] Step 3:

[1354] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[1355] Step 4:

[1356] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[1357] Step 5:

[1358] The server generates the necessary database queries based on the analysis results of the NLP engine. For example, it generates queries related to "last year's energy consumption" and "this year's energy consumption."

[1359] Step 6:

[1360] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[1361] Step 7:

[1362] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[1363] Step 8:

[1364] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[1365] Step 9:

[1366] The server generates a response based on the analysis results. For example, it might create a specific response such as, "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[1367] Step 10:

[1368] The server sends the generated response to the terminal as an HTTP response.

[1369] Step 11:

[1370] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[1371] (Example 1)

[1372] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1373] In modern building management, there is a demand for efficient management even for non-experts. However, current systems are difficult for users without specialized knowledge to operate, making it difficult to obtain information quickly and accurately. Furthermore, advanced technology is required to extract and analyze necessary information from vast amounts of data. Solving these problems is essential.

[1374] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1375] In this invention, the server includes means for receiving questions entered in natural language, natural language processing means for analyzing the questions and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for users to easily input questions in natural language and quickly and accurately obtain the necessary information, even without specialized knowledge.

[1376] "Natural language" refers to the language system that humans use on a daily basis, and is expressed through sound or writing.

[1377] "Means for receiving questions entered in natural language" refers to devices or software that receive questions entered by users in natural language and incorporate them into the system.

[1378] "Natural language processing means" refers to technologies and algorithms that analyze input natural language text, understand its context and meaning, and extract necessary information.

[1379] "Query generation means" refers to devices or software that generate query commands for a database based on analyzed information.

[1380] "Data analysis means" refers to processing devices or software used to analyze data obtained from a database and derive answers to user questions.

[1381] "Answer generation means" refers to devices or software that generate answers for the user based on analysis results.

[1382] "Means of display" refers to devices or software that display the generated answers in a way that users can verify.

[1383] "Tokenization" refers to the process of dividing natural language text into smaller units such as words and phrases.

[1384] Morphological analysis refers to the process of breaking down words into smaller parts and analyzing their basic forms in order to understand the meaning and role of each word that makes up a natural language text.

[1385] A "database" refers to a system for storing, efficiently managing, and retrieving collections of data.

[1386] "Energy consumption" refers to the amount of energy used over a specific period.

[1387] "Carbon dioxide emissions" refers to the amount of carbon dioxide emitted during a specific period.

[1388] "Difference" refers to the difference in quantity or numerical value between two things being compared.

[1389] "Savings" refers to the amount of money reduced by a particular action or measure.

[1390] An "HTTP request" is a protocol used by web browsers and other clients to request data from a server.

[1391] This invention relates to a building management system that acquires necessary data from questions entered in natural language, analyzes it, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[1392] System Configuration

[1393] This invention comprises the following main components:

[1394] 1. Means for receiving questions entered in natural language.

[1395] The terminal receives questions entered by the user through a dedicated interface. These questions are in natural language and do not require any special formatting. For example, it accepts questions such as, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[1396] 2. Natural Language Processing Means

[1397] The server passes the received question to a natural language processing (NLP) engine for analysis. Specifically, it uses natural language processing libraries such as spaCy and NLTK to tokenize and morphologically analyze the question, understand its context, and extract the necessary information.

[1398] 3. Query generation means

[1399] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." Specifically, it generates an SQL statement like this: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[1400] 4. Data Analysis Methods

[1401] The server uses the generated SQL query to query the database and retrieve the necessary data. Next, it analyzes that data, compares energy consumption and carbon dioxide emissions, and calculates the amount of savings.

[1402] 5. Answer generation means

[1403] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[1404] 6. Means for displaying the generated response

[1405] The device displays the received responses to the user. This allows the user to easily obtain specific answers to their questions.

[1406] Specific example

[1407] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[1408] 1. The user enters the question from the management terminal.

[1409] "Have you reduced energy and carbon emissions compared to last year? How much money are you saving?"

[1410] 2. The terminal receives user input and sends it to the server.

[1411] 3. The server receives the question and analyzes it using an NLP engine. For example, it uses libraries such as spaCy or NLTK to perform tokenization and morphological analysis to understand the question.

[1412] 4. The server generates an SQL query based on the analysis results.

[1413] "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[1414] 5. The server sends queries to the database and retrieves the necessary data. A database management system such as MySQL or PostgreSQL is used.

[1415] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[1416] 7. The server generates an answer based on the analysis results.

[1417] "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[1418] 8. The server sends the generated response to the terminal.

[1419] 9. The device displays the received response to the user.

[1420] This allows users to easily input questions in natural language, even without specialized knowledge, and quickly and accurately obtain the information they need.

[1421] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1422] Step 1: User enters question

[1423] Users enter questions in natural language using a dedicated interface on the management terminal. These questions do not require a special format as they are subject to natural language processing. For example, they might enter something like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[1424] Input: Question in natural language format

[1425] Output: Data containing the question content

[1426] Step 2: Sending from the terminal to the server

[1427] The terminal receives the question entered by the user and sends it to the server as an HTTP request. This request contains the question and information related to the user.

[1428] Input: Data containing the question content

[1429] Output: HTTP request containing the question data

[1430] Step 3: Server receives and analyzes the question.

[1431] The server parses the received HTTP request and extracts the question content. Next, it passes the question to a natural language processing (NLP) engine for analysis. For example, it might tokenize the question using libraries such as spaCy or NLTK and then perform morphological analysis to understand the context.

[1432] Input: HTTP request (contains the question)

[1433] Output: Tokenized and morphologically analyzed question data

[1434] Step 4: Generate queries to the database

[1435] The server generates specific SQL queries for the database based on the information extracted from the NLP engine. For example, it creates queries to retrieve information about "last year's energy consumption" and "this year's energy consumption." The specific SQL statements are as follows:

[1436] Example: SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;

[1437] Input: Tokenized and morphologically analyzed question data

[1438] Output: SQL query against the database

[1439] Step 5: Execute queries on the database

[1440] The server sends the generated SQL query to the database and retrieves the necessary data. The database management system used is typically MySQL or PostgreSQL.

[1441] Input: SQL query

[1442] Output: Data retrieved from the database

[1443] Step 6: Data Analysis

[1444] The server analyzes the acquired data. Specifically, it compares energy consumption and carbon dioxide emissions from last year and this year, and calculates the amount of savings from the difference. This allows it to provide specific answers to user questions.

[1445] Input: Data retrieved from the database

[1446] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved)

[1447] Step 7: Generating the answer

[1448] The server generates responses in a user-friendly format based on the analysis results. For example, it might create a response like, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This resulted in savings of approximately 1.2 million yen."

[1449] Input: Analysis results

[1450] Output: Generated answer

[1451] Step 8: Sending the response from the server to the terminal

[1452] The server sends the generated response to the terminal as an HTTP response.

[1453] Input: Generated answer

[1454] Output: HTTP response (response content)

[1455] Step 9: Displaying the response via the device

[1456] The terminal displays the received response on the user interface. This allows the user to easily obtain specific answers to their questions.

[1457] Input: HTTP response (response content)

[1458] Output: Answer displayed in the user interface

[1459] In this way, users can easily input questions in natural language without needing specialized knowledge, and quickly and accurately obtain the necessary information.

[1460] (Application Example 1)

[1461] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1462] In factory management, it is crucial for managers and workers to understand operating conditions and equipment status in real time. However, conventional systems require specialized knowledge, and data collection and analysis are time-consuming. Furthermore, the inability to easily ask and answer questions via voice input hinders efficient management. To solve these problems, a system is needed that accepts questions in natural language and provides quick and accurate answers.

[1463] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1464] In this invention, the server includes means for receiving questions input by voice, voice recognition means for converting the questions into text, natural language processing means for analyzing the text and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating answers based on the analysis results, and means for displaying the generated answers. This makes it possible for managers and workers to query the operating status of the factory and the status of equipment in real time using voice and obtain answers quickly and accurately.

[1465] "Means for receiving questions entered via voice" refers to a function that recognizes machine speech and captures that voice data.

[1466] "Speech recognition means" refers to a technology that analyzes received speech data and converts it into corresponding text.

[1467] "Natural language processing tools" are functions that analyze text-based questions, understand their context and content, and extract necessary information.

[1468] A "query generation method" is a technology that generates request statements, such as SQL queries, for querying a database based on information extracted through natural language processing.

[1469] A "data analysis tool" is a function that analyzes data obtained from a database and derives appropriate answers to questions.

[1470] "Answer generation method" refers to a technology that creates answers in a user-friendly format based on data analysis results.

[1471] "Means of display" refers to display devices or display software that provide the generated answers to the user visually.

[1472] This invention is a system for factory management that accepts questions using voice and provides answers in real time. This system enables factory managers and workers to efficiently understand the operating status and equipment status of the factory through voice.

[1473] The main components of this system include speech recognition software, a natural language processing engine, a database management system, and smart glasses. Specifically, it uses the following hardware and software:

[1474] Hardware to use

[1475] Smart glasses: Receiving and displaying voice input

[1476] Server: Data processing and database management

[1477] Software to use

[1478] Speech recognition software (e.g., Google Cloud Speech-to-Text): Converts speech to text.

[1479] Natural language processing engines (e.g., SpaCy and NLTK): Question analysis

[1480] Database management system (e.g., MySQL): for storing data and executing queries.

[1481] The specific process of the system is as follows:

[1482] Voice input

[1483] Workers and managers input questions by voice into smart glasses. For example, questions could include, "How many machine malfunctions have there been this week?" or "What is the current energy consumption?"

[1484] Speech recognition

[1485] The smart glasses convert the input audio into text using speech recognition software and send that text data to a server.

[1486] question analysis

[1487] The server analyzes the received text data using a natural language processing engine to understand the context and content of the question and extract the necessary information. For example, it performs tokenization and morphological analysis to obtain specific information for querying the database.

[1488] Query generation and data retrieval

[1489] Based on the analysis results, an SQL query is generated for the database. The server uses this query to retrieve the necessary data from the database.

[1490] Data analysis and response generation

[1491] The server analyzes the data obtained from the database and generates specific answers to the questions. For example, it might generate an answer such as, "There have been 3 machine failures this week, and the current energy consumption is 1000kWh."

[1492] Display the answer

[1493] The generated response is sent from the server to the smart glasses and displayed on the screen.

[1494] Specific example

[1495] When an administrator asks, "Please tell me the machine's operating hours for this month," the system processes the request using the following steps:

[1496] 1. Recognize speech and convert it to text.

[1497] 2. Analyze the relevant text using natural language processing.

[1498] 3. Send a query to the database and retrieve the necessary data.

[1499] 4. Analyze the obtained data and generate the answer.

[1500] 5. Display the answer on smart glasses.

[1501] Example of a prompt

[1502] "I'd like to know the operating hours for each machine this month."

[1503] "Please tell me the number of malfunctions that occurred this month."

[1504] As a result, this system allows managers and workers to efficiently perform factory management tasks.

[1505] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1506] Step 1:

[1507] The user inputs a question by voice into the smart glasses. For example, they might say, "How many machine failures were there this week?" At this point, the input is the user's voice.

[1508] Step 2:

[1509] Smart glasses use speech recognition software (e.g., Google Cloud Speech-to-Text) to convert speech to text. They analyze the speech data and generate corresponding text data. The output is the corresponding text data.

[1510] Step 3:

[1511] The terminal sends the generated text data to the server as an HTTP request. The input is text data, and the output is an HTTP request.

[1512] Step 4:

[1513] The server analyzes the received text data using a natural language processing engine (e.g., SpaCy or NLTK). Specifically, it performs tokenization and morphological analysis to extract the context and keywords of the question. The input is text data, and the output is the extracted keywords and contextual information.

[1514] Step 5:

[1515] The server generates an SQL query to query the database based on the extracted information. For example, a query like "SELECT COUNT() FROM malfunction_logs WHERE week = 'current_week';" is generated. The input is the extracted information, and the output is the generated SQL query.

[1516] Step 6:

[1517] The server sends the generated SQL query to the database management system (e.g., MySQL) and retrieves the necessary data. The input is the SQL query, and the output is the data returned from the database.

[1518] Step 7:

[1519] The server analyzes the acquired data using data analysis tools and generates specific answers to questions. For example, it might generate an answer such as, "There were 3 machine failures this week." The input is data obtained from the database, and the output is the generated answer.

[1520] Step 8:

[1521] The server sends the generated response to the smart glasses as an HTTP response. The input is the generated response, and the output is the HTTP response.

[1522] Step 9:

[1523] The smart glasses display the received response as text data on the screen. The input is the response as an HTTP response, and the output is the text displayed on the screen.

[1524] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1525] This invention relates to a building management system that analyzes questions entered in natural language and the user's emotions, acquires and analyzes necessary data, and provides answers to the user. This system is designed to enable efficient building management even for users without specialized knowledge.

[1526] System Processing Overview

[1527] 1. User input of question

[1528] Users enter questions through a dedicated interface on the management terminal. For example, they might enter a question like, "Have you reduced energy and carbon emissions compared to last year? How much money can you save?"

[1529] 2. Sending from the terminal to the server

[1530] The questions entered by the user are sent from the management terminal to the server as an HTTP request. This request includes the question content and user-related information.

[1531] 3. Server receives and analyzes the query.

[1532] The server passes the received question to a natural language processing (NLP) engine and an emotion engine for analysis. The NLP engine understands the context of the question and extracts the necessary information. The emotion engine recognizes the user's emotions as expressed in the question.

[1533] 4. Generating queries to the database

[1534] The server generates specific SQL queries for the database based on the information extracted by the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[1535] 5. Execute queries on the database

[1536] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[1537] 6. Data Analysis

[1538] The server analyzes the acquired data to obtain specific analysis results regarding the user's questions and emotions. This includes comparisons of differences in energy consumption and carbon dioxide emissions.

[1539] 7. Generating the answer

[1540] The server generates responses based on analysis results and the user's emotional state. For example, it might create a specific response such as, "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen." The emotion engine adjusts the tone and expression of the response according to the user's emotions.

[1541] 8. Sending responses from the server to the terminal.

[1542] The response generated by the server is sent to the user's management terminal as an HTTP response.

[1543] 9. Displaying responses via the device

[1544] The user's management terminal displays the received responses. This allows the user to easily obtain answers to their questions.

[1545] Specific example

[1546] Question: Have you reduced energy and carbon emissions compared to last year? How much money have you saved?

[1547] 1. The user enters the question from the management terminal.

[1548] Example: "Have you reduced your energy and carbon emissions compared to last year? How much money can you save?"

[1549] 2. The terminal receives user input and sends it to the server.

[1550] 3. The server receives the question and analyzes it using the NLP engine and the emotion engine.

[1551] The NLP engine understands the context and extracts the necessary information. The emotion engine recognizes the user's emotions.

[1552] 4. The server generates an SQL query based on the analysis results.

[1553] Example: "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X;"

[1554] 5. The server sends a query to the database and retrieves the necessary data.

[1555] 6. The server analyzes the data and compares energy consumption and carbon dioxide emissions. Furthermore, it calculates the amount of savings.

[1556] 7. The server generates a response based on the analysis results and the user's emotional state.

[1557] Example: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. This resulted in savings of approximately 1.2 million yen."

[1558] 8. The server sends the generated response to the terminal.

[1559] 9. The device displays the received response.

[1560] This invention allows users to easily input questions in natural language and quickly obtain necessary information, even without specialized knowledge. Furthermore, the emotion engine provides responses tailored to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[1561] The following describes the processing flow.

[1562] Step 1:

[1563] The user enters questions through a dedicated interface on the management terminal. For example, they might enter questions such as, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1564] Step 2:

[1565] The terminal receives user input and sends the question to the server in the form of an HTTP request. The request includes the question and user-related information.

[1566] Step 3:

[1567] The server parses the received request and passes the question to the natural language processing (NLP) engine. This prepares the engine to understand the context of the question and extract the necessary information.

[1568] Step 4:

[1569] The server's NLP engine tokenizes the question and performs morphological analysis. This process breaks down each part of the question, analyzing its context and meaning.

[1570] Step 5:

[1571] The server's sentiment engine analyzes the user's emotional elements contained in the question. This allows the server to understand the user's emotional state at the time the question was asked.

[1572] Step 6:

[1573] The server generates the necessary database queries based on the analysis results of the NLP engine and the emotion engine. For example, queries regarding "last year's energy consumption" and "this year's energy consumption" are generated.

[1574] Step 7:

[1575] The server uses the generated SQL query to query the database. At this point, it verifies that a proper database connection has been established.

[1576] Step 8:

[1577] The server retrieves the necessary data from the database. For example, data such as "last year's energy consumption" and "this year's energy consumption" may be returned.

[1578] Step 9:

[1579] The server analyzes the acquired data to obtain specific analysis results in response to user questions. This includes comparing differences in energy consumption and carbon dioxide emissions.

[1580] Step 10:

[1581] The server generates a response based on the analysis results. In this process, it uses the results of the emotion engine to generate a response with a tone and language appropriate to the user's emotional state. For example, it might create a specific and considerate response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen."

[1582] Step 11:

[1583] The server sends the generated response to the terminal as an HTTP response.

[1584] Step 12:

[1585] The device displays the received response on the user interface. The user can easily understand the information related to the question through the displayed response.

[1586] (Example 2)

[1587] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1588] In building management, there is a need for a means that allows users to efficiently and effectively acquire and manage information without requiring specialized knowledge. However, conventional systems require complex operations and specialized knowledge, which can hinder daily operations. Furthermore, providing quick responses that take user emotions into consideration is difficult, and improving the user experience is also a challenge.

[1589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1590] In this invention, the server includes means for receiving a question entered in natural language, natural language processing means for analyzing the question and extracting necessary information, sentiment analysis means for analyzing the user's emotions contained in the question, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer that takes the user's emotions into consideration based on the analysis results, and means for displaying the generated answer. As a result, the user can enter a question in natural language, quickly obtain the necessary information without requiring specialized knowledge, and be provided with an answer that is appropriate to the user's emotions.

[1591] "Means for receiving questions entered in natural language" refers to an interface for receiving text data entered by a user in natural language.

[1592] "Natural language processing means" refers to technologies for analyzing received natural language text data and extracting intent and important information.

[1593] "Emotion analysis methods" are technologies that analyze a user's emotions from natural language text data and identify their emotional state.

[1594] A "query generation method" is a technology that generates query statements (SQL queries) to be executed against a database based on the analyzed information.

[1595] "Data analysis methods" refer to techniques for analyzing data obtained from databases and extracting and calculating useful information.

[1596] "Answer generation means" refers to a technology for generating responses to users in natural language form based on analyzed data and the user's emotional state.

[1597] "Means for displaying generated answers" refers to an interface for visually displaying generated answers to the user.

[1598] This invention relates to a building management system that analyzes questions entered by users in natural language and provides appropriate answers to those questions. This system is designed to enable efficient building management even for users without specialized knowledge.

[1599] Hardware and software to use

[1600] The main hardware and software components of this system include:

[1601] Management terminal: A device that provides an interface for users to enter questions. Examples include PCs, tablets, and smartphones.

[1602] Server: The primary device responsible for parsing questions, generating queries to the database, performing data analysis, and generating answers.

[1603] Natural language processing engine: Software such as the Google Cloud Natural Language API that analyzes questions and extracts important information.

[1604] Emotion analysis engine: Software for analyzing user emotions, such as IBM Watson Tone Analyzer.

[1605] Database: A database that stores data on a building's energy consumption and carbon dioxide emissions.

[1606] Interface software: Software that retrieves questions entered by the user, sends them to the server, and receives and displays the answers from the server.

[1607] Specific operation of the system

[1608] Users input questions in natural language using a dedicated interface on the management terminal. For example, they might input a question like, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1609] The management terminal retrieves this question as text data and sends it to the server as an HTTP request. This request includes the question content and user-related identification information.

[1610] The server passes the received question to a natural language processing engine and an emotion analysis engine for analysis. The natural language processing engine understands the context of the question and extracts important information. The emotion analysis engine analyzes the user's emotions and understands the user's state.

[1611] Based on the analyzed information, the server generates a specific SQL query to execute against the database. For example, it might generate a query like "SELECT energy_last_year, energy_this_year, co2_last_year, co2_this_year FROM energy_data WHERE building_id = X".

[1612] The server sends the generated query to the database and retrieves the necessary data. The retrieved data is then analyzed by data analysis tools, for example, to compare energy consumption and carbon dioxide emissions, and to calculate savings.

[1613] The server generates specific responses in natural language based on the analysis results and the user's emotional state. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[1614] The generated response is sent to the management terminal as an HTTP response. The management terminal receives this response and displays it visually to the user.

[1615] Examples of specific cases and prompt statements

[1616] As a concrete example, the following prompt statements are possible:

[1617] Question: "Have you reduced energy and carbon dioxide emissions compared to last year? How much money are you saving?"

[1618] Answer: "Compared to last year, energy consumption decreased by 15% and carbon dioxide emissions decreased by 8%. We have saved approximately 1.2 million yen."

[1619] This invention allows users to input questions in natural language without requiring specialized knowledge of building management, and to obtain quick and appropriate answers. Furthermore, the emotion analysis engine provides answers that respond to the user's emotions, improving the user experience. This system can significantly improve the efficiency of building management.

[1620] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1621] Step 1:

[1622] User input of question

[1623] User: Use the dedicated interface on the management terminal to enter questions in natural language. For example, "Have you reduced energy and carbon dioxide emissions compared to last year? How much money can you save?"

[1624] Input: Text data entered in natural language.

[1625] Output: The question text displayed on the interface.

[1626] Step 2:

[1627] Sending from the terminal to the server

[1628] Terminal: Retrieves the user's input as text data, generates an HTTP request, and sends it to the server.

[1629] Input: Text data of the question.

[1630] Output: HTTP request containing the question content.

[1631] Step 3:

[1632] Server receives and analyzes questions.

[1633] Server: Parses the received HTTP request and extracts the question as text. This is then passed to the natural language processing engine and sentiment analysis engine for analysis.

[1634] Server: Uses a natural language processing engine (e.g., Google Cloud Natural Language API) to understand the context of the question and extract important information.

[1635] Server: Uses a sentiment analysis engine (e.g., IBM Watson Tone Analyzer) to identify the user's emotions.

[1636] Input: HTTP request containing the question content.

[1637] Output: Analyzed information (keywords, context, emotional state).

[1638] Step 4:

[1639] Generating queries to the database

[1640] Server: Generates SQL queries to the database based on information obtained from the NLP engine and emotion engine. For example, queries to retrieve "last year's energy consumption" or "this year's energy consumption".

[1641] Input: Analyzed information (keywords, context, emotional state).

[1642] Output: The generated SQL query.

[1643] Step 5:

[1644] Execute queries against the database

[1645] Server: Uses the generated SQL query to query the database and retrieve the necessary data.

[1646] Server: Establishes a database connection and executes queries while handling errors.

[1647] Input: SQL query.

[1648] Output: Data retrieved from the database.

[1649] Step 6:

[1650] Data Analysis

[1651] Server: Analyzes data obtained from the database to compare energy consumption and carbon dioxide emissions, and calculate savings.

[1652] Server: Performs calculations and calculates the difference and savings.

[1653] Input: Data retrieved from a database.

[1654] Output: Analysis results (difference in energy consumption, difference in carbon dioxide emissions, amount saved).

[1655] Step 7:

[1656] Answer generation

[1657] Server: Based on the analysis results and the user's emotional state, it generates specific responses in natural language. For example, it might create a response such as, "Compared to last year, energy consumption has decreased by 15% and carbon dioxide emissions have decreased by 8%. This has resulted in savings of approximately 1.2 million yen." The tone and expression of the response are adjusted according to the user's emotions by the emotion analysis engine.

[1658] Input: Analysis results, user's emotional state.

[1659] Output: Generated answer text.

[1660] Step 8:

[1661] Sending responses from the server to the terminal.

[1662] Server: Sends the generated response text to the management terminal as an HTTP response.

[1663] Server: Formats the response into JSON format or similar and generates an HTTP response.

[1664] Input: Generated response text.

[1665] Output: HTTP response.

[1666] Step 9:

[1667] Displaying responses via device

[1668] Terminal: Analyzes the HTTP response received from the server and displays it to the user in a visually easy-to-understand format. For example, it might display: "Energy consumption decreased by 15% and carbon dioxide emissions decreased by 8% compared to last year. This has resulted in savings of approximately 1.2 million yen."

[1669] Input: HTTP response.

[1670] Output: The answer text displayed on the terminal.

[1671] (Application Example 2)

[1672] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1673] Traditional building management systems made it difficult for users without specialized knowledge to effectively utilize the system. Furthermore, the lack of means to provide quick and appropriate answers to user questions hindered the user experience. This made it particularly difficult to obtain information regarding energy management and production efficiency, impeding the efficiency of management operations. Additionally, the failure to consider user emotions in response generation resulted in low user satisfaction.

[1674] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving a question input in natural language, natural language processing means for analyzing the question and extracting necessary information, query generation means for querying a database based on the extracted information, data analysis means for analyzing data obtained from the database, answer generation means for generating an answer based on the analysis results, means for displaying the generated answer, and sentiment analysis means for analyzing the user's emotions. As a result, the user can quickly obtain specific information regarding energy management and production efficiency through questions in natural language without specialized knowledge. In addition, the user experience is improved because appropriate answers are provided based on the user's emotions.

[1675] "Natural language" refers to the language that humans use on a daily basis, and is a means of conveying information in the form of writing and conversation.

[1676] "Natural language processing means" refers to technologies for analyzing natural language, such as questions and commands, and extracting necessary information.

[1677] A "query generation method" is a means of generating a query for a database based on the extracted information.

[1678] "Data analysis methods" refer to techniques for analyzing data obtained from databases to derive useful information and trends.

[1679] A "response generation method" is a means of generating responses for users based on the results of data analysis.

[1680] "Display means" refers to a means of displaying the generated response so that the user can confirm it.

[1681] An "emotion analysis tool" is a means of analyzing the user's emotions contained in questions and commands, and enabling responses that correspond to those emotions.

[1682] "Energy consumption" refers to the total amount of energy consumed within a certain period.

[1683] "Carbon dioxide emissions" refers to the total amount of carbon dioxide emitted within a certain period.

[1684] "Production efficiency" is an indicator that represents the efficiency of production results in relation to the resources invested in a factory or production line.

[1685] A "factory management system" is a system that comprehensively handles the information necessary for the operation and management of a factory, and supports efficient operations.

[1686] This invention relates to a building management system that analyzes questions entered in natural language, retrieves necessary information from a database, analyzes it, generates answers, and takes user emotions into consideration. Specific embodiments for carrying out this invention are described below.

[1687] The system primarily uses the following hardware and software:

[1688] Server (question analysis and data processing)

[1689] Smartphone (user device)

[1690] Database server (data storage)

[1691] The specific software used includes the following:

[1692] Natural Language Processing Engine (NLPEngine)

[1693] Sentiment Engine

[1694] Database connection library (MySQL Connector)

[1695] The user inputs a question in natural language from their smartphone. For example, they might input, "How much did this month's energy consumption increase compared to last month, and what was the reason?" The smartphone receives the question and sends it to the server as an HTTP request. Upon receiving the question, the server automatically uses NLPEngine to analyze the context of the question. NLPEngine performs tokenization and morphological analysis to extract the necessary information from the question.

[1696] Next, the server uses a SentimentEngine to analyze the user's emotions. This identifies the emotional elements contained in the question. Based on the analyzed information, an SQL query is generated for the database. The generated query is sent to the database server, and the necessary data is retrieved.

[1697] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. For example, it can determine how much energy consumption has increased compared to the previous month, and whether the cause is the introduction of a new production line.

[1698] Based on the analysis results, the response generation system generates an appropriate response for the user. Using an emotion analysis engine, the response is adjusted to a tone that matches the user's emotions. For example, "This month's energy consumption has increased by 10% compared to last month. The main reason is the introduction of a new production line."

[1699] The generated response is sent from the server to the user's smartphone as an HTTP response. The smartphone then displays the received response to the user. This allows users, even without specialized knowledge, to quickly obtain information on energy management and production efficiency using natural language and utilize it in their management activities.

[1700] As a concrete example, when the question "How much did this month's energy consumption increase compared to last month, and what was the reason?" is entered, the system, after going through the aforementioned analysis flow, generates the answer "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." Based on the same question, the AI ​​model can be given example prompts such as "Please tell me the reason for the fluctuation in the factory's energy consumption" and "What caused the increase in energy consumption compared to last month?"

[1701] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1702] Step 1:

[1703] The user enters a question from their smartphone. For example, they might enter, "How much did this month's energy consumption increase compared to last month, and what was the reason?" In this case, the smartphone receives the question in natural language as input and displays the question on the smartphone as output.

[1704] Step 2:

[1705] The device (smartphone) sends the received question to the server as an HTTP request. This request includes the question content and user-specific information. It receives a request containing a natural language question and user information as input, and sends that request to the server as output.

[1706] Step 3:

[1707] The server receives an HTTP request and uses a natural language processing engine (NLPEngine) to analyze the context of the question. Specifically, it tokenizes the natural language question received as input, performs morphological analysis, and understands the context of the question. As a result, the necessary information is extracted, and the extracted information is obtained as output.

[1708] Step 4:

[1709] The server uses a SentimentEngine to analyze the user's emotions. Based on the questions received as input, emotion analysis is performed, and the user's emotional state is identified. The user's emotion data is obtained as output.

[1710] Step 5:

[1711] The server generates an SQL query to the database based on the extracted information and sentiment data. It takes the extracted information and sentiment data as input and outputs the generated SQL query. For example, a query like "SELECT energy_last_month, energy_this_month, reason FROM factory_energy_data WHERE factory_id = X;" is generated.

[1712] Step 6:

[1713] The server sends the generated SQL query to the database server and retrieves the necessary data. It receives the generated SQL query as input and queries the database server. The retrieved data is obtained as output.

[1714] Step 7:

[1715] The server analyzes the acquired data using data analysis tools to obtain analysis results regarding energy consumption and production efficiency. It receives acquired data as input and performs data analysis such as calculating fluctuations in energy consumption and savings. The analysis results are obtained as output.

[1716] Step 8:

[1717] The server generates responses based on analysis results and user sentiment data. It receives analysis results and sentiment data as input and adjusts the response to match the user's sentiment. For example, it might generate a response such as, "This month's energy consumption increased by 10% compared to last month. The main reason is the introduction of a new production line." The generated response is obtained as output.

[1718] Step 9:

[1719] The server sends the generated response to the user's smartphone as an HTTP response. It receives the generated response as input and sends that response to the smartphone as output.

[1720] Step 10:

[1721] The device (smartphone) displays the received response to the user. It receives the response as input and displays that response on the smartphone screen as output. This allows the user to obtain a specific answer to the question.

[1722] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1723] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1724] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1725] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1726] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1727] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1728] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1729] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1730] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1731] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1732] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1733] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1734] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1735] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1736] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1737] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1738] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1739] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1740] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1741] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1742] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1743] The following is further disclosed regarding the embodiments described above.

[1744] (Claim 1)

[1745] A means for receiving questions entered in natural language,

[1746] A natural language processing means for analyzing the question and extracting necessary information,

[1747] A query generation means that queries the database based on the extracted information,

[1748] A data analysis method for analyzing data obtained from a database,

[1749] A response generation means that generates a response based on the analysis results,

[1750] A means of displaying the generated answer,

[1751] A system that includes this.

[1752] (Claim 2)

[1753] The system according to claim 1, wherein the natural language processing means performs tokenization and morphological analysis to understand the context of the question.

[1754] (Claim 3)

[1755] The system according to claim 1, wherein the data analysis means compares energy consumption and carbon dioxide emissions and calculates the amount of savings from the difference.

[1756] "Example 1"

[1757] (Claim 1)

[1758] A means for receiving questions entered in natural language,

[1759] A natural language processing means for analyzing the question and extracting necessary information,

[1760] A query generation means that queries the database based on the extracted information,

[1761] A data analysis method for analyzing data obtained from a database,

[1762] A response generation means that generates a response based on the analysis results,

[1763] A means of displaying the generated answer,

[1764] A system that includes this.

[1765] (Claim 2)

[1766] The system according to claim 1, wherein the natural language processing means performs tokenization and morphological analysis to understand the context of the question.

[1767] (Claim 3)

[1768] The system according to claim 1, wherein the data analysis means compares energy consumption and carbon dioxide emissions and calculates the amount of savings from the difference.

[1769] "Application Example 1"

[1770] (Claim 1)

[1771] A means of receiving questions entered via voice,

[1772] A speech recognition means that converts the question into text,

[1773] A natural language processing means that analyzes the characters in question and extracts the necessary information,

[1774] A query generation means that queries the database based on the extracted information,

[1775] A data analysis method for analyzing data obtained from a database,

[1776] A response generation means that generates a response based on the analysis results,

[1777] A means for displaying the generated response,

[1778] A system that includes this.

[1779] (Claim 2)

[1780] The system according to claim 1, wherein the natural language processing means performs tokenization and morphological analysis to understand the context of the question.

[1781] (Claim 3)

[1782] The system according to claim 1, wherein the data analysis means compares machine operation information and failure information and calculates operational efficiency from the difference.

[1783] "Example 2 of combining an emotion engine"

[1784] (Claim 1)

[1785] A means for receiving questions entered in natural language,

[1786] A natural language processing means for analyzing the question and extracting necessary information,

[1787] A sentiment analysis tool that analyzes the user's emotions contained in the question,

[1788] A query generation means that queries the database based on the extracted information,

[1789] A data analysis method for analyzing data obtained from a database,

[1790] A response generation means that generates a response considering the user's emotions based on the analysis results,

[1791] A means of displaying the generated answer,

[1792] A system that includes this.

[1793] (Claim 2)

[1794] The system according to claim 1, wherein the natural language processing means performs tokenization and morphological analysis to understand the context of the question.

[1795] (Claim 3)

[1796] The system according to claim 1, wherein the data analysis means compares energy consumption and carbon dioxide emissions and calculates the amount of savings from the difference.

[1797] "Application example 2 when combining with an emotional engine"

[1798] (Claim 1)

[1799] A means for receiving questions entered in natural language,

[1800] A natural language processing means for analyzing the question and extracting necessary information,

[1801] A query generation means that queries the database based on the extracted information,

[1802] A data analysis method for analyzing data obtained from a database,

[1803] A response generation means that generates a response based on the analysis results,

[1804] A means of displaying the generated answer,

[1805] A system that includes emotion analysis tools for analyzing user emotions.

[1806] (Claim 2)

[1807] Natural language processing tools perform tokenization and morphological analysis to understand the context of the question.

[1808] The system according to claim 1.

[1809] (Claim 3)

[1810] The data analysis method compares energy consumption and carbon dioxide emissions, and calculates the amount of savings from the difference.

[1811] Furthermore, based on the data analysis results, it generates answers regarding the factory's production efficiency and energy management.

[1812] The system according to claim 1. [Explanation of symbols]

[1813] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving questions entered in natural language, A natural language processing means for analyzing the question and extracting necessary information, A query generation means that queries the database based on the extracted information, A data analysis method for analyzing data obtained from a database, A response generation means that generates a response based on the analysis results, A means of displaying the generated answer, A system that includes this.

2. The system according to claim 1, wherein the natural language processing means performs tokenization and morphological analysis to understand the context of the question.

3. The system according to claim 1, wherein the data analysis means compares energy consumption and carbon dioxide emissions and calculates the amount of savings from the difference.

Images