system

Abstract

Provide a system. [Solution] a data collection method that periodically crawls websites and stores grant information in a database; a diary input means for receiving diary data input by a user; A natural language processing means for extracting keywords from the user's diary and identifying themes that interest or require the user based on the keywords; a subsidy information matching means for matching the extracted keywords with subsidy information in a database and listing matching subsidy information; a notification sending means for notifying a user terminal of the applicable subsidy information; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, there are various government support and subsidy programs, but obtaining information on them requires a lot of time and effort. In particular, ordinary users often find it difficult to find the support program that best suits them from the vast amount of information available, resulting in a lack of convenience. They may also miss the timing to apply and miss out on support they could have received. This invention aims to solve these problems by providing a system that automatically provides appropriate subsidy information through diary entries, eliminating the need for users to actively search for subsidy information. [Means for solving the problem]

[0005] The present invention is a system including a data collection means, a diary input means, a natural language processing means, a subsidy information matching means, and a notification sending means. The data collection means periodically crawls websites and stores subsidy information in a database. The diary input means receives diary data entered by users. The natural language processing means extracts keywords from the user's diary and, based on these, identifies themes that the user is interested in or needs. The subsidy information matching means compares the extracted keywords with subsidy information in the database and lists matching subsidy information. The notification sending means notifies the user's terminal of matching subsidy information. In this way, users can efficiently obtain suitable subsidy information.

[0006] "Data Collection Measures" means devices or software that periodically crawl websites, collect grant information, and store it in a database.

[0007] The "diary input means" is an interface or application that allows the user to input diary data and send it to the system.

[0008] "Natural language processing means" refers to a device or software that extracts keywords and phrases from the diary data entered by the user and, based on these, identifies themes that the user is interested in or needs.

[0009] The "subsidy information matching means" is a device or software that matches the extracted keywords and phrases with subsidy information in a database and lists information on matching subsidies and support systems.

[0010] The "notification sending means" is a device or software for notifying the user's terminal of applicable subsidy information. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means.

[0033] To implement this system, the server first uses a data collection tool to crawl official government and related agency websites to collect subsidy information. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. The collected data (e.g., subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0034] Users enter diary data through a dedicated app or web interface for entering one-line diary entries. This diary entry tool is responsible for sending the entered data to the server in an appropriate format (e.g., JSON format).

[0035] Once the server receives the diary data, it analyzes the diary content using natural language processing. This process uses Python libraries such as NLTK and spaCy to extract keywords and sentiment from the diary text. This allows the server to evaluate how the information obtained from the user's diary relates to subsidy and support programs.

[0036] Next, the subsidy information matching means compares the extracted keywords and emotion information with subsidy information stored in a database. This matching process can use a search engine such as ElasticSearch (registered trademark). This creates a list of subsidies and support programs available to the user.

[0037] Finally, the notification sending means sends the list of matching subsidy information to the user's terminal, and the user receives the notification from the terminal and can check specific details and how to apply.

[0038] Specific examples

[0039] For example, suppose a server crawls a government subsidy information site on a certain Monday and finds that a new subsidy for the "Eco-Reform Support Project" has been added. This information is stored in the server's database.

[0040] That evening, the user uses the app to enter a diary entry such as, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." When this diary entry data is sent to the server, the natural language processing means extracts the keywords "renovation" and "eco" and recognizes that it matches data related to "eco-friendly renovation support projects."

[0041] The next day, detailed information about the "Eco Reform Support Project" is sent from the server to the user's terminal via the notification sending means. The user can use this information to consider applying for a subsidy.

[0042] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner, and do not miss the timing to apply.

[0043] The processing flow will be explained below.

[0044] Step 1: Data collection

[0045] The server periodically crawls official government and agency websites. It uses Python's BeautifulSoup and Scrapy to parse the HTML of the webpages and extract the grant information section. The extracted grant information (e.g., grant name, summary, application conditions, deadline, etc.) is stored in a database.

[0046] Step 2: Enter your diary entry

[0047] Users enter their daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user locally, checks the contents, encodes them into an appropriate format (e.g., JSON), and sends them to the server.

[0048] Step 3: Receiving and saving diary data

[0049] The server receives the diary data sent from the terminal and stores the diary data in a database.

[0050] Step 4: Natural Language Processing

[0051] The server periodically (e.g., every night) retrieves the stored diary data and performs natural language processing (NLP) using Python's NLTK or spaCy to extract keywords and phrases from the diary text and identify themes that the user is interested in or needs.

[0052] Step 5: Matching grant information

[0053] The server compares the keywords and themes extracted through natural language processing with the grant information stored in the database, and uses a search engine such as Elasticsearch for the matching process to list grant information that matches the user's needs.

[0054] Step 6: Prepare and send notifications

[0055] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. The server then sends the notification message and data including detailed information to the user's device.

[0056] Step 7: User Notification

[0057] The terminal decodes the subsidy information data received from the server. The terminal displays a notification to the user, which includes important information such as the name of the subsidy, a summary, application conditions, and deadline. The user can review the notification and consider applying for the subsidy based on the detailed information.

[0058] Example 1

[0059] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0060] In today's world, various types of subsidy information are scattered across the web, making it difficult to efficiently collect this information and provide appropriate information that meets users' needs. In particular, it takes a great deal of time and effort for users to find appropriate subsidy information based on the information and emotions they have gained in their daily lives. The present invention solves this problem.

[0061] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0062] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means, which enable the server to periodically crawl government and related organization websites, automatically collect and store subsidy information, match the subsidy information based on keywords extracted from the user's diary, and promptly notify the user of appropriate information to their terminal.

[0063] "Data collection means" is a system component that has the function of periodically analyzing information sources on the network and automatically collecting and storing various information.

[0064] A "diary input means" is a system component that provides an interface for a user to input text data and transmit the data to the server in an appropriate format.

[0065] A "natural language processing means" is a system component that extracts specific keywords and emotions from text data and analyzes the context based on them.

[0066] The "information matching means" is a system component that compares extracted keywords and emotional information with stored information in the database.

[0067] The "notification sending means" is a system component that has a function for notifying the user's terminal of the collation result.

[0068] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means. Implementing the present invention involves the following processes.

[0069] First, the server uses data collection tools to crawl official government and related agency websites. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. For example, it can extract information about the "Eco-Renovation Support Project" from a particular page. The extracted data (subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0070] Next, the user enters diary data through a dedicated app or web interface. This diary entry method sends the entered text data to the server in an appropriate format (e.g., JSON format). For example, if a user enters the diary entry "Today I thought about renovating my house. I'm interested in eco-friendly renovations," it will be sent to the server.

[0071] When the server receives the diary data, it analyzes the diary contents using natural language processing. This analysis process uses Python libraries such as NLTK and spaCy. Keywords and emotions are extracted from the diary text. For example, keywords such as "renovation" and "eco" are extracted, and the strength of the user's interest is determined through sentiment analysis.

[0072] Next, the server uses information matching tools to match the extracted keywords and emotion information with subsidy information stored in a database. This process can be performed using a search engine such as Elasticsearch. For example, it can confirm that the keywords "renovation" and "eco" match the subsidy information for the "Eco Renovation Support Project."

[0073] Finally, the server uses the notification sending means to send a list of applicable subsidy information to the user's device. For example, detailed information about the "Eco Reform Support Project" is sent as a notification to the user's smartphone or computer. The user receives this notification and can check the specific details and how to apply.

[0074] Specific examples

[0075] As an example, suppose a server crawls a government subsidy information website on a certain Monday and saves information about a new "Eco Renovation Support Project" in the database. That evening, a user enters a diary entry through the app, stating, "Today I thought about renovating my house. I'm interested in eco-renovations." The server receives the diary data and uses natural language processing to extract keywords such as "renovation" and "eco." As a result, it recognizes that these keywords match data related to the "Eco Renovation Support Project." The next day, the server notifies the user's device of detailed information about the "Eco Renovation Support Project" through a notification sending means. The user can use this information to consider applying for a subsidy.

[0076] Examples of prompt statements

[0077] For example, an example of a prompt for a generative AI model is, "A user has entered a one-line diary entry indicating that they are interested in subsidy programs. Please explain the process of using natural language processing technology to extract subsidy information related to the eco-renovation support project from the content and send a notification to the user."

[0078] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0079] Step 1:

[0080] The server uses a data collection method to periodically crawl information sources on the network. Specifically, it uses Python's BeautifulSoup and Scrapy to analyze the HTML structure of web pages and extract subsidy information. For example, it collects information about an "eco-renovation support project" from a government website. The input is a list of URLs for the target sites, and the output is structured data of subsidy information (name, summary, application conditions, deadline, etc.). This data is stored in a database for use in the next step.

[0081] Step 2:

[0082] A user enters a one-line diary entry through a dedicated app or web interface. This diary entry method converts the text entered by the user into JSON format and sends it to the server. For example, a user might enter, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." The input is the user's diary text, and the output is the JSON-formatted data of that text.

[0083] Step 3:

[0084] The server uses natural language processing to analyze the diary data it receives. Specifically, it uses Python's NLTK and spaCy to extract keywords and emotions from the diary text. For example, it identifies keywords such as "renovation" and "eco" and analyzes that the user is interested in eco-friendly renovations. The input is diary data in JSON format, and the output is the extracted keywords and emotion data.

[0085] Step 4:

[0086] The server uses information matching methods to match the extracted keywords and sentiment information with subsidy information in the database. Elasticsearch is used for this process. For example, it verifies that keywords such as "renovation" and "eco" match subsidy information for the "Eco Renovation Support Project." The input is keywords and sentiment information, and the output is a list of related subsidy information.

[0087] Step 5:

[0088] The server uses the notification sending means to send the relevant subsidy information to the user's terminal. This notification contains detailed information about the subsidies available to the user. For example, information about the "Eco-Reform Support Project" is sent to the user's smartphone or PC. The input is a list of relevant subsidy information, and the output is a notification sent to the user's terminal.

[0089] (Application example 1)

[0090] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] Previously, it was difficult for brick-and-mortar store owners and managers to efficiently obtain appropriate subsidy information. In particular, because subsidy information was scattered across government and related agency websites, there was a lack of means to quickly access the necessary information. Furthermore, there was a risk that missing important information, such as subsidy application conditions and deadlines, could have a negative impact on business operations. The present invention aims to solve these problems and provide an efficient system that enables brick-and-mortar store owners and managers to obtain appropriate subsidy information in a timely manner.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0093] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means. This allows owners and managers of brick-and-mortar stores to automatically obtain appropriate subsidy information by entering a short diary entry about their daily activities and management through an application that can be installed and used on a smartphone or tablet. Specifically, the server periodically crawls websites to store subsidy information in a database, extracts keywords and emotions from the diary entries, matches them with subsidy information, and sends notifications of relevant subsidy information to users' devices in a timely manner.

[0094] The "data collection means" refers to the means for periodically crawling websites to collect subsidy information and storing it in a database as structured data.

[0095] The "diary input means" is a means by which a user can input a short diary entry about the business status, new ideas, and capital investments through a dedicated interface, and transmit the data to the server in an appropriate format.

[0096] The "natural language processing means" is a means for extracting keywords and emotions from the user's diary and analyzing the information.

[0097] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database, and identifying relevant subsidies and support systems.

[0098] The "notification sending means" is a means for notifying the user's terminal of a list of applicable subsidy information and support systems in a timely manner and providing detailed information.

[0099] "Owners and managers of physical stores" refers to business operators of commercial facilities or service businesses, and refers to individuals or organizations that manage and operate their own stores.

[0100] "Applications installed on smartphones and tablets" are dedicated applications installed on mobile devices, and are a means for users to enter diary entries and receive notifications of subsidy information.

[0101] "Structured data" refers to a data format in which collected subsidy information is organized in a specific format (e.g., JSON, XML, etc.) and stored in a database.

[0102] "Keywords" refer to important words and phrases extracted from the text of a user's diary and are used to match with subsidy information.

[0103] "Emotion" refers to the results of analyzing the emotions and feelings contained in the text of the user's diary, and is used to evaluate the relevance to subsidy information.

[0104] The present invention provides a system that provides an application that can be installed and used by owners and managers of physical stores on smartphones or tablets to obtain appropriate subsidy information. The following hardware and software are used to implement the present invention.

[0105] 1. Data collection methods:

[0106] The server periodically crawls government and related organization websites using web crawling libraries such as BeautifulSoup and Scrapy to collect subsidy information, and stores the collected data in a database as structured data.

[0107] 2. Diary entry method:

[0108] Users use a dedicated application installed on their smartphone or tablet to enter short diary entries about their daily activities and business management. The diary data is then sent to the server in an appropriate format (e.g., JSON format).

[0109] 3. Natural Language Processing Tools:

[0110] The server uses natural language processing libraries such as spacy and NLTK to extract keywords and sentiment from the diary text. This analysis process evaluates how the information obtained from the diary relates to the grant information.

[0111] 4. Subsidy information matching method:

[0112] Elasticsearch is used as a subsidy information matching tool to compare the extracted keywords and sentiment information with subsidy information stored in a database, thereby generating a list of subsidies and support programs available to users.

[0113] 5. Notification Method:

[0114] Using KafkaProducer or similar as a notification sending method, a list of applicable subsidy information is sent to the user's device in a timely manner. The user receives the notification from their device and can check specific details and how to apply.

[0115] Adding specific examples

[0116] For example, suppose a server crawls a government subsidy information website on Monday and finds that a new subsidy for the "Eco-Renovation Support Project" has been added. This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm interested in eco-renovations." When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "eco" and recognizes that it matches the data for the "Eco-Renovation Support Project."

[0117] Example prompt sentence:

[0118] A user enters a diary entry in the app as follows:

[0119] Today I was thinking about renovating my shop. I wish there was a grant to use for the interior.

[0120] This process allows the system to notify the user of appropriate grant information (e.g., "Interior Renovation Assistance Grant").

[0121] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner.

[0122] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0123] Step 1:

[0124] Data collection

[0125] The server periodically crawls government and related agency websites using web crawling libraries such as BeautifulSoup and Scrapy. It analyzes the HTML structure of the websites it accesses and extracts grant information (e.g., grant name, summary, application conditions, deadline, etc.). The extracted data is saved as structured data (e.g., JSON format).

[0126] (Input): Website URL

[0127] (Data processing): HTML analysis, information extraction

[0128] (Output): Structured data (JSON format)

[0129] Step 2:

[0130] Database storage

[0131] The server stores the collected structured data in Elasticsearch, which then serves as a database for future searches and matching. Specifically, the data is indexed using Elasticsearch's API.

[0132] (Input): Structured data (JSON format)

[0133] (Data processing): Database indexing

[0134] (Output): Index data on Elasticsearch

[0135] Step 3:

[0136] Diary entry

[0137] Users use a dedicated application installed on their smartphones or tablets to enter short diaries about their daily activities and business status. The diaries entered by the user are sent to the server in an appropriate format (e.g., JSON format).

[0138] (Input): User's diary text

[0139] (Data processing): Text format conversion (JSON format)

[0140] (Output): Data sent to the server

[0141] Step 4:

[0142] Natural Language Processing

[0143] The server analyzes the received diary data using natural language processing tools (such as Spacy or NLTK). Through this analysis, keywords and emotional information are extracted from the diary. Specifically, important words and phrases are identified from the text and an associated emotional score is calculated.

[0144] (Input): Diary data (JSON format)

[0145] (Data processing): Text analysis, keyword extraction, sentiment analysis

[0146] (Output): Keywords and sentiment information

[0147] Step 5:

[0148] Information Matching

[0149] The server uses the extracted keywords and sentiment information to match the subsidy information stored in Elasticsearch. Specifically, it uses Elasticsearch's search function to search for subsidy information that matches the keywords and lists the most relevant subsidy information.

[0150] (Input): Keywords and emotion information

[0151] (Data processing): Information search and matching

[0152] (Output): List of grant information

[0153] Step 6:

[0154] Send notifications

[0155] The server sends the list of subsidy information to the user's device via a messaging system such as KafkaProducer. The user receives the notification on their smartphone or tablet and can check the specific subsidy information and how to apply.

[0156] (Input): Grant information list

[0157] (Data processing): Notification message generation and sending

[0158] (Output): Notification to user terminal

[0159] This series of steps enables store owners and managers to obtain the most appropriate subsidy information in a timely manner.

[0160] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0161] The present invention is a system that includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0162] Data collection methods

[0163] The server periodically crawls official government and agency websites to collect grant information. Using Python libraries such as BeautifulSoup and Scrapy, the server parses the HTML of web pages and extracts sections containing grant information. The extracted data (e.g., grant name, summary, application requirements, deadline, etc.) is stored in a database as structured data.

[0164] Diary entry method

[0165] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0166] Natural language processing tools and emotion engines

[0167] Once the diary data is received, the server performs natural language processing (NLP). Using libraries such as Python's NLTK and spaCy, it extracts keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. This emotional information is used to more fully evaluate the user's interests and themes of their needs.

[0168] Subsidy information matching method

[0169] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0170] Notification sending method

[0171] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0172] Specific examples

[0173] For example, suppose a server crawls a government subsidy information site on a certain Monday and retrieves subsidy information about a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database.

[0174] That evening, the user enters a diary entry through the app, saying, "Today I thought about renovating my house, especially looking for ways to be more environmentally friendly." In addition, the emotion engine recognizes that the user has positive feelings about this content. When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions.

[0175] Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. The notification sending means notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time based on the user's positive emotion. The user can consider applying for a subsidy based on this information.

[0176] In this way, by implementing the present invention, users can efficiently obtain appropriate subsidy information through daily input including emotional information, and will not miss the timing to apply.

[0177] The processing flow will be explained below.

[0178] Step 1: Data collection

[0179] The server periodically crawls official government and agency websites. Using crawling libraries such as Python's BeautifulSoup and Scrapy, the server parses the HTML of the webpages and extracts sections containing grant information. This information includes the grant name, summary, application requirements, deadline, etc. The extracted data is then stored in a structured format in a database.

[0180] Step 2: Enter your diary entry

[0181] Users can enter daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user, checks the content, encodes it into an appropriate format such as JSON, and sends it to the server. This process ensures smooth entry for the user.

[0182] Step 3: Receiving and saving diary data

[0183] The server receives the diary data sent from the device and stores it in a database on the server. The diary data also includes metadata necessary for further analysis, such as text content and date information.

[0184] Step 4: Natural Language Processing and Sentiment Analysis

[0185] The server performs natural language processing (NLP) on the stored diary data. Specifically, it uses Python's NLTK and spaCy libraries to extract keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. For example, from the diary entry "I'm interested in eco-friendly renovations," it extracts keywords such as "renovation" and "eco" to recognize positive emotions.

[0186] Step 5: Matching grant information

[0187] The server compares the keywords extracted by natural language processing and the emotion information extracted by the emotion engine with the subsidy information stored in the database, using a search engine such as Elasticsearch to efficiently list the most relevant subsidy information.

[0188] Step 6: Prepare and send notifications

[0189] The server then encodes the list of matching grants into an appropriate format (e.g., JSON) to notify the user of the list. This data includes important information such as the grant name, summary, application requirements, and deadline.

[0190] Step 7: User Notification

[0191] The terminal analyzes and decodes the subsidy information data received from the server. The terminal displays a notification to the user. This notification includes detailed information about the subsidy and the deadline. The user can review the notification and consider applying for the subsidy based on the detailed information. The notification sending means also optimizes the timing of the notification, taking into account the user's emotional state.

[0192] As a concrete example, suppose the server collects new subsidy information for the "Environmental Protection Eco-Renovation Support Project" on Monday. That evening, the user writes in their diary, "Today I thought about renovating my house. I'm especially looking for ways to be more environmentally friendly." The emotion engine recognizes that the user has positive feelings about this topic. The next day, a notification about the "Environmental Protection Eco-Renovation Support Project" is sent to the user's device, allowing the user to consider applying for the subsidy based on the detailed information. This series of processes allows the user to efficiently obtain subsidy information that is appropriate for them and avoid missing the timing to apply.

[0193] Example 2

[0194] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0195] Conventional subsidy information systems have had problems in that it is difficult for users to manually search for subsidy information that meets their needs or to receive notifications at the appropriate time. In addition, there is no way to obtain subsidy information that reflects the user's daily activities and interests, making it difficult to collect information efficiently.

[0196] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0197] In this invention, the server includes a data collection means, a diary input means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means, thereby enabling the provision of efficient and appropriate subsidy information based on the user's daily input and emotion information.

[0198] "Data collection means" refers to a means of crawling websites on the Internet to collect necessary information and storing it in a database as structured data.

[0199] "Diary input means" refers to a means for collecting data through an application or web interface that allows users to input their daily activities and thoughts.

[0200] The "natural language processing means" is a means for analyzing input text data and performing processing to extract keywords and phrases.

[0201] The "emotion engine means" is a means for analyzing the emotion information contained in the diary data of the user and for evaluating in detail the themes that interest and need of the user based on that information.

[0202] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database.

[0203] The "notification sending means" is a means for notifying the user's terminal of information at an appropriate time.

[0204] This invention is a system including a data collection means, a diary entry means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0205] Data collection methods

[0206] The server periodically crawls official government and related agency websites using Python web scraping libraries such as BeautifulSoup and Scrapy. The HTML data of the crawled web pages is analyzed to extract the necessary grant information (e.g., grant name, summary, application conditions, deadline, etc.). This extracted data is stored as structured data in the server's database.

[0207] Diary entry method

[0208] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0209] Natural language processing tools

[0210] The server uses Python libraries such as NLTK and spaCy to perform natural language processing on the received diary data, extracting keywords and phrases from the diary text.

[0211] Emotion Engine Means

[0212] The server utilizes an emotion engine to extract emotion information from the user's diary data, which is used to more precisely evaluate the user's themes of interest and needs.

[0213] Subsidy information matching method

[0214] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0215] Notification sending method

[0216] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) to notify the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0217] Specific examples

[0218] For example, suppose a server crawls a government subsidy information website on a Monday and retrieves subsidy information for a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm especially looking for environmentally friendly ways." The emotion engine also recognizes that the user has positive emotions about this entry. When this diary entry is sent to the server, the natural language processing unit extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions. Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. Based on the user's positive emotions, the notification sending unit notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time. The user can use this information to consider applying for a subsidy.

[0219] Prompt Sentence Examples

[0220] "Please explain how the system works to suggest appropriate grant information based on keywords extracted from the user's diary and the positive emotions associated with them."

[0221] By inputting this prompt sentence into a generative AI model, it is possible to generate an easy-to-understand explanation of the operation of the system of the present invention and the coordination of each means.

[0222] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0223] Step 1:

[0224] The server periodically crawls official government and related agency websites using data collection tools. Specifically, it uses Python's BeautifulSoup and Scrapy libraries to parse the HTML data of web pages and extract subsidy information. The input is the web page URL, and the output is subsidy information (e.g., subsidy name, summary, application conditions, deadline, etc.). The extracted subsidy information is stored in a database as structured data.

[0225] Step 2:

[0226] Users enter their daily diary entries through a dedicated application or web interface. Specifically, they enter their diary entry in a text box and press the send button. The input is the user's diary entry text, and the output is diary data encoded in JSON format. The device temporarily stores the entered diary entry data locally and sends it to the server after passing validation.

[0227] Step 3:

[0228] The server performs natural language processing (NLP) on the received diary data. Specifically, it uses Python's NLTK and spaCy libraries to tokenize the text and extract keywords and phrases. The input is the user's diary data, and the output is the extracted keywords and phrases.

[0229] Step 4:

[0230] The server uses an emotion engine to extract emotional information from the user's diary data. Specifically, it uses an emotion analysis library (e.g., TextBlob or VADER) to evaluate emotions (positive, negative, neutral). The input is the user's diary data, and the output is emotional information.

[0231] Step 5:

[0232] The server compares the keywords and emotion information extracted through natural language processing with the subsidy information stored in the database. Specifically, it uses a search engine such as Elasticsearch to submit keywords as queries and search for related subsidy information. The input is keywords and emotion information, and the output is a list of subsidy information that matches the user.

[0233] Step 6:

[0234] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. Specifically, it uses a web framework such as Flask or Django to send the data to the user in JSON format. The input is a list of subsidy information, and the output is notification data in JSON format.

[0235] Step 7:

[0236] The device displays the received notification data to the user. Specifically, it displays information to the user using push notifications or in-app pop-up notifications. The input is notification data in JSON format, and the output is the notification information displayed to the user.

[0237] These processing steps allow users to efficiently obtain appropriate subsidy information through everyday input, including emotional information, and avoid missing the timing to apply.

[0238] (Application example 2)

[0239] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0240] Conventional subsidy information presentation systems have difficulty taking into account a user's daily activities and emotions, and have difficulty providing security information tailored to specific situations at the appropriate time. As a result, users may miss necessary security information or be unable to respond to risks and suffer damage. This invention aims to more effectively support users by utilizing users' diary data and emotional information to automatically match and notify them of appropriate security information.

[0241] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0242] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a notification sending means, and a security information matching means, which enables the server to automatically extract and present appropriate security information from the user's daily activity record.

[0243] "Data collection means" refers to the means of periodically crawling the source website, collecting the necessary data, and storing it in a database.

[0244] The "diary input means" is a means for providing an interface for the user to input daily events and thoughts.

[0245] The "natural language processing means" is a means for analyzing and extracting keywords and phrases from the user's diary data.

[0246] The "emotion engine" is a means for analyzing and extracting emotional information from a user's diary data.

[0247] The "notification sending means" is a means for sending necessary notifications to the user based on the analyzed information.

[0248] The "security information matching means" is a means for matching security information based on data extracted by the natural language processing means and emotion engine.

[0249] MODE FOR CARRYING OUT THE INVENTION

[0250] This invention is a system that automatically extracts and presents appropriate security information from a user's daily activity record, and includes a data collection means, a diary input means, a natural language processing means, an emotion engine, a security information matching means, and a notification sending means.

[0251] Hardware and Software Configuration

[0252] To realize this system, the following hardware and software are used:

[0253] Server: Responsible for overall control of data collection and processing.

[0254] Smartphone: Allows users to enter diary entries and receive notifications.

[0255] Python: Implements the program across all elements.

[0256] BeautifulSoup: Web crawling is used as a means of collecting data.

[0257] Requests: Communicate with the web server.

[0258] spaCy: A natural language processing tool that performs text analysis of diary data.

[0259] smtplib: Sends emails as a means of sending notifications.

[0260] System Operation Overview

[0261] Data collection

[0262] The server periodically crawls websites that provide security-related information and collects the data. To do this, it uses BeautifulSoup and Requests to parse the HTML of web pages and extract sections that contain security information. The extracted data is stored in a database as structured data.

[0263] Diary entry

[0264] Users input their daily events and emotions using a dedicated smartphone application. This input data is temporarily stored on the device and then sent to the server in JSON format.

[0265] Natural Language Processing and Sentiment Analysis

[0266] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases. It also uses an emotion engine to analyze the emotional information expressed in the diary by the user. This allows it to evaluate the themes that interest and require the user.

[0267] Security Information Matching

[0268] The server then uses the extracted keywords and sentiment information to match security information stored in a database. This process uses a search engine and database queries, resulting in a list of security information that matches the user's needs.

[0269] Send notifications

[0270] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the security information title, summary, and risk level. The device receives this and notifies the user via smartphone push notification or email. Email notifications are also sent using smtplib.

[0271] Specific examples

[0272] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0273] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0274] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0275] Finally, the server sends a notification containing this security risk information to the user's smartphone at the appropriate time, informing them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0276] Prompt example

[0277] "When you enter today's events (such as 'Set up VPN') in the Secure Diary app, you will be notified of the latest applicable security advisory information. Get security information about VPNs."

[0278] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0279] Step 1: Crawling for security information using data collection methods

[0280] The server periodically crawls websites that provide security-related information. It uses BeautifulSoup and Requests to parse the HTML of the web pages and extract sections containing security information. The server then stores the extracted data (e.g., the title, summary, and risk level of the security advisory) in a database as structured data.

[0281] Input: URL of a website with security-related information

[0282] Output: Security information stored in the database

[0283] Step 2: Enter the user's activity record using the diary entry tool

[0284] Users input their daily experiences and thoughts using a dedicated smartphone application. This input data is temporarily stored locally and then sent to the server in an appropriate format (e.g., JSON format).

[0285] Input: User's diary data (text)

[0286] Output: Diary data sent to the server (JSON format)

[0287] Step 3: Analysis by natural language processing and sentiment engine

[0288] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases, and also analyzes emotional information (positive, negative, anxious, etc.) from the user's diary data using an emotion engine.

[0289] Input: Diary data sent to the server (JSON format)

[0290] Output: Extracted keywords and sentiment information

[0291] Step 4: Data verification through security information matching

[0292] The server compares the keywords and sentiment information extracted through natural language processing with the security information stored in the database, using a search engine and database queries to produce a list of security information that matches the user's needs.

[0293] Input: Extracted keywords and sentiment information, security information stored in the database

[0294] Output: List of security information that matches the user

[0295] Step 5: Notify the user via notification delivery methods

[0296] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes the title, summary, and risk level of the security information. The device (smartphone) receives this and notifies the user via push notification or email. Email notification uses smtplib.

[0297] Input: A list of security information that matches the user

[0298] Output: Notification sent to the user (push notification or email)

[0299] Concrete examples

[0300] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0301] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0302] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0303] Finally, the server sends this security risk information to the user's smartphone at the appropriate time, notifying them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0304] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0305] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0306] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0307] [Second embodiment]

[0308] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0309] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0310] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0311] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0312] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0313] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0314] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0315] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0316] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0317] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0318] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0319] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0320] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means.

[0321] To implement this system, the server first uses a data collection tool to crawl official government and related agency websites to collect subsidy information. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. The collected data (e.g., subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0322] Users enter diary data through a dedicated app or web interface for entering one-line diary entries. This diary entry tool is responsible for sending the entered data to the server in an appropriate format (e.g., JSON format).

[0323] Once the server receives the diary data, it analyzes the diary content using natural language processing. This process uses Python libraries such as NLTK and spaCy to extract keywords and sentiment from the diary text. This allows the server to evaluate how the information obtained from the user's diary relates to subsidy and support programs.

[0324] Next, the subsidy information matching tool compares the extracted keywords and sentiment information with the subsidy information stored in the database. This matching process can use a search engine such as Elasticsearch. This creates a list of subsidies and support programs available to the user.

[0325] Finally, the notification sending means sends the list of matching subsidy information to the user's terminal, and the user receives the notification from the terminal and can check specific details and how to apply.

[0326] Specific examples

[0327] For example, suppose a server crawls a government subsidy information site on a certain Monday and finds that a new subsidy for the "Eco-Reform Support Project" has been added. This information is stored in the server's database.

[0328] That evening, the user uses the app to enter a diary entry such as, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." When this diary entry data is sent to the server, the natural language processing means extracts the keywords "renovation" and "eco" and recognizes that it matches data related to "eco-friendly renovation support projects."

[0329] The next day, detailed information about the "Eco Reform Support Project" is sent from the server to the user's terminal via the notification sending means. The user can use this information to consider applying for a subsidy.

[0330] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner, and do not miss the timing to apply.

[0331] The processing flow will be explained below.

[0332] Step 1: Data collection

[0333] The server periodically crawls official government and agency websites. It uses Python's BeautifulSoup and Scrapy to parse the HTML of the webpages and extract the grant information section. The extracted grant information (e.g., grant name, summary, application conditions, deadline, etc.) is stored in a database.

[0334] Step 2: Enter your diary entry

[0335] Users enter their daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user locally, checks the contents, encodes them into an appropriate format (e.g., JSON), and sends them to the server.

[0336] Step 3: Receiving and saving diary data

[0337] The server receives the diary data sent from the terminal and stores the diary data in a database.

[0338] Step 4: Natural Language Processing

[0339] The server periodically (e.g., every night) retrieves the stored diary data and performs natural language processing (NLP) using Python's NLTK or spaCy to extract keywords and phrases from the diary text and identify themes that the user is interested in or needs.

[0340] Step 5: Matching grant information

[0341] The server compares the keywords and themes extracted through natural language processing with the grant information stored in the database, and uses a search engine such as Elasticsearch for the matching process to list grant information that matches the user's needs.

[0342] Step 6: Prepare and send notifications

[0343] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. The server then sends the notification message and data including detailed information to the user's device.

[0344] Step 7: User Notification

[0345] The terminal decodes the subsidy information data received from the server. The terminal displays a notification to the user, which includes important information such as the name of the subsidy, a summary, application conditions, and deadline. The user can review the notification and consider applying for the subsidy based on the detailed information.

[0346] Example 1

[0347] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0348] In today's world, various types of subsidy information are scattered across the web, making it difficult to efficiently collect this information and provide appropriate information that meets users' needs. In particular, it takes a great deal of time and effort for users to find appropriate subsidy information based on the information and emotions they have gained in their daily lives. The present invention solves this problem.

[0349] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0350] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means, which enable the server to periodically crawl government and related organization websites, automatically collect and store subsidy information, match the subsidy information based on keywords extracted from the user's diary, and promptly notify the user of appropriate information to their terminal.

[0351] "Data collection means" is a system component that has the function of periodically analyzing information sources on the network and automatically collecting and storing various information.

[0352] A "diary input means" is a system component that provides an interface for a user to input text data and transmit the data to the server in an appropriate format.

[0353] A "natural language processing means" is a system component that extracts specific keywords and emotions from text data and analyzes the context based on them.

[0354] The "information matching means" is a system component that compares extracted keywords and emotional information with stored information in the database.

[0355] The "notification sending means" is a system component that has a function for notifying the user's terminal of the collation result.

[0356] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means. Implementing the present invention involves the following processes.

[0357] First, the server uses data collection tools to crawl official government and related agency websites. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. For example, it can extract information about the "Eco-Renovation Support Project" from a particular page. The extracted data (subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0358] Next, the user enters diary data through a dedicated app or web interface. This diary entry method sends the entered text data to the server in an appropriate format (e.g., JSON format). For example, if a user enters the diary entry "Today I thought about renovating my house. I'm interested in eco-friendly renovations," it will be sent to the server.

[0359] When the server receives the diary data, it analyzes the diary contents using natural language processing. This analysis process uses Python libraries such as NLTK and spaCy. Keywords and emotions are extracted from the diary text. For example, keywords such as "renovation" and "eco" are extracted, and the strength of the user's interest is determined through sentiment analysis.

[0360] Next, the server uses information matching tools to match the extracted keywords and emotion information with subsidy information stored in a database. This process can be performed using a search engine such as Elasticsearch. For example, it can confirm that the keywords "renovation" and "eco" match the subsidy information for the "Eco Renovation Support Project."

[0361] Finally, the server uses the notification sending means to send a list of applicable subsidy information to the user's device. For example, detailed information about the "Eco Reform Support Project" is sent as a notification to the user's smartphone or computer. The user receives this notification and can check the specific details and how to apply.

[0362] Specific examples

[0363] As an example, suppose a server crawls a government subsidy information website on a certain Monday and saves information about a new "Eco Renovation Support Project" in the database. That evening, a user enters a diary entry through the app, stating, "Today I thought about renovating my house. I'm interested in eco-renovations." The server receives the diary data and uses natural language processing to extract keywords such as "renovation" and "eco." As a result, it recognizes that these keywords match data related to the "Eco Renovation Support Project." The next day, the server notifies the user's device of detailed information about the "Eco Renovation Support Project" through a notification sending means. The user can use this information to consider applying for a subsidy.

[0364] Examples of prompt statements

[0365] For example, an example of a prompt for a generative AI model is, "A user has entered a one-line diary entry indicating that they are interested in subsidy programs. Please explain the process of using natural language processing technology to extract subsidy information related to the eco-renovation support project from the content and send a notification to the user."

[0366] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0367] Step 1:

[0368] The server uses a data collection method to periodically crawl information sources on the network. Specifically, it uses Python's BeautifulSoup and Scrapy to analyze the HTML structure of web pages and extract subsidy information. For example, it collects information about an "eco-renovation support project" from a government website. The input is a list of URLs for the target sites, and the output is structured data of subsidy information (name, summary, application conditions, deadline, etc.). This data is stored in a database for use in the next step.

[0369] Step 2:

[0370] A user enters a one-line diary entry through a dedicated app or web interface. This diary entry method converts the text entered by the user into JSON format and sends it to the server. For example, a user might enter, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." The input is the user's diary text, and the output is the JSON-formatted data of that text.

[0371] Step 3:

[0372] The server uses natural language processing to analyze the diary data it receives. Specifically, it uses Python's NLTK and spaCy to extract keywords and emotions from the diary text. For example, it identifies keywords such as "renovation" and "eco" and analyzes that the user is interested in eco-friendly renovations. The input is diary data in JSON format, and the output is the extracted keywords and emotion data.

[0373] Step 4:

[0374] The server uses information matching methods to match the extracted keywords and sentiment information with subsidy information in the database. Elasticsearch is used for this process. For example, it verifies that keywords such as "renovation" and "eco" match subsidy information for the "Eco Renovation Support Project." The input is keywords and sentiment information, and the output is a list of related subsidy information.

[0375] Step 5:

[0376] The server uses the notification sending means to send the relevant subsidy information to the user's terminal. This notification contains detailed information about the subsidies available to the user. For example, information about the "Eco-Reform Support Project" is sent to the user's smartphone or PC. The input is a list of relevant subsidy information, and the output is a notification sent to the user's terminal.

[0377] (Application example 1)

[0378] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0379] Previously, it was difficult for brick-and-mortar store owners and managers to efficiently obtain appropriate subsidy information. In particular, because subsidy information was scattered across government and related agency websites, there was a lack of means to quickly access the necessary information. Furthermore, there was a risk that missing important information, such as subsidy application conditions and deadlines, could have a negative impact on business operations. The present invention aims to solve these problems and provide an efficient system that enables brick-and-mortar store owners and managers to obtain appropriate subsidy information in a timely manner.

[0380] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0381] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means. This allows owners and managers of brick-and-mortar stores to automatically obtain appropriate subsidy information by entering a short diary entry about their daily activities and management through an application that can be installed and used on a smartphone or tablet. Specifically, the server periodically crawls websites to store subsidy information in a database, extracts keywords and emotions from the diary entries, matches them with subsidy information, and sends notifications of relevant subsidy information to users' devices in a timely manner.

[0382] The "data collection means" refers to the means for periodically crawling websites to collect subsidy information and storing it in a database as structured data.

[0383] The "diary input means" is a means by which a user can input a short diary entry about the business status, new ideas, and capital investments through a dedicated interface, and transmit the data to the server in an appropriate format.

[0384] The "natural language processing means" is a means for extracting keywords and emotions from the user's diary and analyzing the information.

[0385] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database, and identifying relevant subsidies and support systems.

[0386] The "notification sending means" is a means for notifying the user's terminal of a list of applicable subsidy information and support systems in a timely manner and providing detailed information.

[0387] "Owners and managers of physical stores" refers to business operators of commercial facilities or service businesses, and refers to individuals or organizations that manage and operate their own stores.

[0388] "Applications installed on smartphones and tablets" are dedicated applications installed on mobile devices, and are a means for users to enter diary entries and receive notifications of subsidy information.

[0389] "Structured data" refers to a data format in which collected subsidy information is organized in a specific format (e.g., JSON, XML, etc.) and stored in a database.

[0390] "Keywords" refer to important words and phrases extracted from the text of a user's diary and are used to match with subsidy information.

[0391] "Emotion" refers to the results of analyzing the emotions and feelings contained in the text of the user's diary, and is used to evaluate the relevance to subsidy information.

[0392] The present invention provides a system that provides an application that can be installed and used by owners and managers of physical stores on smartphones or tablets to obtain appropriate subsidy information. The following hardware and software are used to implement the present invention.

[0393] 1. Data collection methods:

[0394] The server periodically crawls government and related organization websites using web crawling libraries such as BeautifulSoup and Scrapy to collect subsidy information, and stores the collected data in a database as structured data.

[0395] 2. Diary entry method:

[0396] Users use a dedicated application installed on their smartphone or tablet to enter short diary entries about their daily activities and business management. The diary data is then sent to the server in an appropriate format (e.g., JSON format).

[0397] 3. Natural Language Processing Tools:

[0398] The server uses natural language processing libraries such as spacy and NLTK to extract keywords and sentiment from the diary text. This analysis process evaluates how the information obtained from the diary relates to the grant information.

[0399] 4. Subsidy information matching method:

[0400] Elasticsearch is used as a subsidy information matching tool to compare the extracted keywords and sentiment information with subsidy information stored in a database, thereby generating a list of subsidies and support programs available to users.

[0401] 5. Notification Method:

[0402] Using KafkaProducer or similar as a notification sending method, a list of applicable subsidy information is sent to the user's device in a timely manner. The user receives the notification from their device and can check specific details and how to apply.

[0403] Adding specific examples

[0404] For example, suppose a server crawls a government subsidy information website on Monday and finds that a new subsidy for the "Eco-Renovation Support Project" has been added. This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm interested in eco-renovations." When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "eco" and recognizes that it matches the data for the "Eco-Renovation Support Project."

[0405] Example prompt sentence:

[0406] A user enters a diary entry in the app as follows:

[0407] Today I was thinking about renovating my shop. I wish there was a grant to use for the interior.

[0408] This process allows the system to notify the user of appropriate grant information (e.g., "Interior Renovation Assistance Grant").

[0409] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner.

[0410] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0411] Step 1:

[0412] Data collection

[0413] The server periodically crawls government and related agency websites using web crawling libraries such as BeautifulSoup and Scrapy. It analyzes the HTML structure of the websites it accesses and extracts grant information (e.g., grant name, summary, application conditions, deadline, etc.). The extracted data is saved as structured data (e.g., JSON format).

[0414] (Input): Website URL

[0415] (Data processing): HTML analysis, information extraction

[0416] (Output): Structured data (JSON format)

[0417] Step 2:

[0418] Database storage

[0419] The server stores the collected structured data in Elasticsearch, which then serves as a database for future searches and matching. Specifically, the data is indexed using Elasticsearch's API.

[0420] (Input): Structured data (JSON format)

[0421] (Data processing): Database indexing

[0422] (Output): Index data on Elasticsearch

[0423] Step 3:

[0424] Diary entry

[0425] Users use a dedicated application installed on their smartphones or tablets to enter short diaries about their daily activities and business status. The diaries entered by the user are sent to the server in an appropriate format (e.g., JSON format).

[0426] (Input): User's diary text

[0427] (Data processing): Text format conversion (JSON format)

[0428] (Output): Data sent to the server

[0429] Step 4:

[0430] Natural Language Processing

[0431] The server analyzes the received diary data using natural language processing tools (such as Spacy or NLTK). Through this analysis, keywords and emotional information are extracted from the diary. Specifically, important words and phrases are identified from the text and an associated emotional score is calculated.

[0432] (Input): Diary data (JSON format)

[0433] (Data processing): Text analysis, keyword extraction, sentiment analysis

[0434] (Output): Keywords and sentiment information

[0435] Step 5:

[0436] Information Matching

[0437] The server uses the extracted keywords and sentiment information to match the subsidy information stored in Elasticsearch. Specifically, it uses Elasticsearch's search function to search for subsidy information that matches the keywords and lists the most relevant subsidy information.

[0438] (Input): Keywords and emotion information

[0439] (Data processing): Information search and matching

[0440] (Output): List of grant information

[0441] Step 6:

[0442] Send notifications

[0443] The server sends the list of subsidy information to the user's device via a messaging system such as KafkaProducer. The user receives the notification on their smartphone or tablet and can check the specific subsidy information and how to apply.

[0444] (Input): Grant information list

[0445] (Data processing): Notification message generation and sending

[0446] (Output): Notification to user terminal

[0447] This series of steps enables store owners and managers to obtain the most appropriate subsidy information in a timely manner.

[0448] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0449] The present invention is a system that includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0450] Data collection methods

[0451] The server periodically crawls official government and agency websites to collect grant information. Using Python libraries such as BeautifulSoup and Scrapy, the server parses the HTML of web pages and extracts sections containing grant information. The extracted data (e.g., grant name, summary, application requirements, deadline, etc.) is stored in a database as structured data.

[0452] Diary entry method

[0453] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0454] Natural language processing tools and emotion engines

[0455] Once the diary data is received, the server performs natural language processing (NLP). Using libraries such as Python's NLTK and spaCy, it extracts keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. This emotional information is used to more fully evaluate the user's interests and themes of their needs.

[0456] Subsidy information matching method

[0457] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0458] Notification sending method

[0459] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0460] Specific examples

[0461] For example, suppose a server crawls a government subsidy information site on a certain Monday and retrieves subsidy information about a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database.

[0462] That evening, the user enters a diary entry through the app, saying, "Today I thought about renovating my house, especially looking for ways to be more environmentally friendly." In addition, the emotion engine recognizes that the user has positive feelings about this content. When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions.

[0463] Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. The notification sending means notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time based on the user's positive emotion. The user can consider applying for a subsidy based on this information.

[0464] In this way, by implementing the present invention, users can efficiently obtain appropriate subsidy information through daily input including emotional information, and will not miss the timing to apply.

[0465] The processing flow will be explained below.

[0466] Step 1: Data collection

[0467] The server periodically crawls official government and agency websites. Using crawling libraries such as Python's BeautifulSoup and Scrapy, the server parses the HTML of the webpages and extracts sections containing grant information. This information includes the grant name, summary, application requirements, deadline, etc. The extracted data is then stored in a structured format in a database.

[0468] Step 2: Enter your diary entry

[0469] Users can enter daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user, checks the content, encodes it into an appropriate format such as JSON, and sends it to the server. This process ensures smooth entry for the user.

[0470] Step 3: Receiving and saving diary data

[0471] The server receives the diary data sent from the device and stores it in a database on the server. The diary data also includes metadata necessary for further analysis, such as text content and date information.

[0472] Step 4: Natural Language Processing and Sentiment Analysis

[0473] The server performs natural language processing (NLP) on the stored diary data. Specifically, it uses Python's NLTK and spaCy libraries to extract keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. For example, from the diary entry "I'm interested in eco-friendly renovations," it extracts keywords such as "renovation" and "eco" to recognize positive emotions.

[0474] Step 5: Matching grant information

[0475] The server compares the keywords extracted by natural language processing and the emotion information extracted by the emotion engine with the subsidy information stored in the database, using a search engine such as Elasticsearch to efficiently list the most relevant subsidy information.

[0476] Step 6: Prepare and send notifications

[0477] The server then encodes the list of matching grants into an appropriate format (e.g., JSON) to notify the user of the list. This data includes important information such as the grant name, summary, application requirements, and deadline.

[0478] Step 7: User Notification

[0479] The terminal analyzes and decodes the subsidy information data received from the server. The terminal displays a notification to the user. This notification includes detailed information about the subsidy and the deadline. The user can review the notification and consider applying for the subsidy based on the detailed information. The notification sending means also optimizes the timing of the notification, taking into account the user's emotional state.

[0480] As a concrete example, suppose the server collects new subsidy information for the "Environmental Protection Eco-Renovation Support Project" on Monday. That evening, the user writes in their diary, "Today I thought about renovating my house. I'm especially looking for ways to be more environmentally friendly." The emotion engine recognizes that the user has positive feelings about this topic. The next day, a notification about the "Environmental Protection Eco-Renovation Support Project" is sent to the user's device, allowing the user to consider applying for the subsidy based on the detailed information. This series of processes allows the user to efficiently obtain subsidy information that is appropriate for them and avoid missing the timing to apply.

[0481] Example 2

[0482] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0483] Conventional subsidy information systems have had problems in that it is difficult for users to manually search for subsidy information that meets their needs or to receive notifications at the appropriate time. In addition, there is no way to obtain subsidy information that reflects the user's daily activities and interests, making it difficult to collect information efficiently.

[0484] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0485] In this invention, the server includes a data collection means, a diary input means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means, thereby enabling the provision of efficient and appropriate subsidy information based on the user's daily input and emotion information.

[0486] "Data collection means" refers to a means of crawling websites on the Internet to collect necessary information and storing it in a database as structured data.

[0487] "Diary input means" refers to a means for collecting data through an application or web interface that allows users to input their daily activities and thoughts.

[0488] The "natural language processing means" is a means for analyzing input text data and performing processing to extract keywords and phrases.

[0489] The "emotion engine means" is a means for analyzing the emotion information contained in the diary data of the user and for evaluating in detail the themes that interest and need of the user based on that information.

[0490] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database.

[0491] The "notification sending means" is a means for notifying the user's terminal of information at an appropriate time.

[0492] This invention is a system including a data collection means, a diary entry means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0493] Data collection methods

[0494] The server periodically crawls official government and related agency websites using Python web scraping libraries such as BeautifulSoup and Scrapy. The HTML data of the crawled web pages is analyzed to extract the necessary grant information (e.g., grant name, summary, application conditions, deadline, etc.). This extracted data is stored as structured data in the server's database.

[0495] Diary entry method

[0496] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0497] Natural language processing tools

[0498] The server uses Python libraries such as NLTK and spaCy to perform natural language processing on the received diary data, extracting keywords and phrases from the diary text.

[0499] Emotion Engine Means

[0500] The server utilizes an emotion engine to extract emotion information from the user's diary data, which is used to more precisely evaluate the user's themes of interest and needs.

[0501] Subsidy information matching method

[0502] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0503] Notification sending method

[0504] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) to notify the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0505] Specific examples

[0506] For example, suppose a server crawls a government subsidy information website on a Monday and retrieves subsidy information for a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm especially looking for environmentally friendly ways." The emotion engine also recognizes that the user has positive emotions about this entry. When this diary entry is sent to the server, the natural language processing unit extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions. Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. Based on the user's positive emotions, the notification sending unit notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time. The user can use this information to consider applying for a subsidy.

[0507] Prompt Sentence Examples

[0508] "Please explain how the system works to suggest appropriate grant information based on keywords extracted from the user's diary and the positive emotions associated with them."

[0509] By inputting this prompt sentence into a generative AI model, it is possible to generate an easy-to-understand explanation of the operation of the system of the present invention and the coordination of each means.

[0510] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0511] Step 1:

[0512] The server periodically crawls official government and related agency websites using data collection tools. Specifically, it uses Python's BeautifulSoup and Scrapy libraries to parse the HTML data of web pages and extract subsidy information. The input is the web page URL, and the output is subsidy information (e.g., subsidy name, summary, application conditions, deadline, etc.). The extracted subsidy information is stored in a database as structured data.

[0513] Step 2:

[0514] Users enter their daily diary entries through a dedicated application or web interface. Specifically, they enter their diary entry in a text box and press the send button. The input is the user's diary entry text, and the output is diary data encoded in JSON format. The device temporarily stores the entered diary entry data locally and sends it to the server after passing validation.

[0515] Step 3:

[0516] The server performs natural language processing (NLP) on the received diary data. Specifically, it uses Python's NLTK and spaCy libraries to tokenize the text and extract keywords and phrases. The input is the user's diary data, and the output is the extracted keywords and phrases.

[0517] Step 4:

[0518] The server uses an emotion engine to extract emotional information from the user's diary data. Specifically, it uses an emotion analysis library (e.g., TextBlob or VADER) to evaluate emotions (positive, negative, neutral). The input is the user's diary data, and the output is emotional information.

[0519] Step 5:

[0520] The server compares the keywords and emotion information extracted through natural language processing with the subsidy information stored in the database. Specifically, it uses a search engine such as Elasticsearch to submit keywords as queries and search for related subsidy information. The input is keywords and emotion information, and the output is a list of subsidy information that matches the user.

[0521] Step 6:

[0522] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. Specifically, it uses a web framework such as Flask or Django to send the data to the user in JSON format. The input is a list of subsidy information, and the output is notification data in JSON format.

[0523] Step 7:

[0524] The device displays the received notification data to the user. Specifically, it displays information to the user using push notifications or in-app pop-up notifications. The input is notification data in JSON format, and the output is the notification information displayed to the user.

[0525] These processing steps allow users to efficiently obtain appropriate subsidy information through everyday input, including emotional information, and avoid missing the timing to apply.

[0526] (Application example 2)

[0527] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] Conventional subsidy information presentation systems have difficulty taking into account a user's daily activities and emotions, and have difficulty providing security information tailored to specific situations at the appropriate time. As a result, users may miss necessary security information or be unable to respond to risks and suffer damage. This invention aims to more effectively support users by utilizing users' diary data and emotional information to automatically match and notify them of appropriate security information.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0530] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a notification sending means, and a security information matching means, which enables the server to automatically extract and present appropriate security information from the user's daily activity record.

[0531] "Data collection means" refers to the means of periodically crawling the source website, collecting the necessary data, and storing it in a database.

[0532] The "diary input means" is a means for providing an interface for the user to input daily events and thoughts.

[0533] The "natural language processing means" is a means for analyzing and extracting keywords and phrases from the user's diary data.

[0534] The "emotion engine" is a means for analyzing and extracting emotional information from a user's diary data.

[0535] The "notification sending means" is a means for sending necessary notifications to the user based on the analyzed information.

[0536] The "security information matching means" is a means for matching security information based on data extracted by the natural language processing means and emotion engine.

[0537] MODE FOR CARRYING OUT THE INVENTION

[0538] This invention is a system that automatically extracts and presents appropriate security information from a user's daily activity record, and includes a data collection means, a diary input means, a natural language processing means, an emotion engine, a security information matching means, and a notification sending means.

[0539] Hardware and Software Configuration

[0540] To realize this system, the following hardware and software are used:

[0541] Server: Responsible for overall control of data collection and processing.

[0542] Smartphone: Allows users to enter diary entries and receive notifications.

[0543] Python: Implements the program across all elements.

[0544] BeautifulSoup: Web crawling is used as a means of collecting data.

[0545] Requests: Communicate with the web server.

[0546] spaCy: A natural language processing tool that performs text analysis of diary data.

[0547] smtplib: Sends emails as a means of sending notifications.

[0548] System Operation Overview

[0549] Data collection

[0550] The server periodically crawls websites that provide security-related information and collects the data. To do this, it uses BeautifulSoup and Requests to parse the HTML of web pages and extract sections that contain security information. The extracted data is stored in a database as structured data.

[0551] Diary entry

[0552] Users input their daily events and emotions using a dedicated smartphone application. This input data is temporarily stored on the device and then sent to the server in JSON format.

[0553] Natural Language Processing and Sentiment Analysis

[0554] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases. It also uses an emotion engine to analyze the emotional information expressed in the diary by the user. This allows it to evaluate the themes that interest and require the user.

[0555] Security Information Matching

[0556] The server then uses the extracted keywords and sentiment information to match security information stored in a database. This process uses a search engine and database queries, resulting in a list of security information that matches the user's needs.

[0557] Send notifications

[0558] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the security information title, summary, and risk level. The device receives this and notifies the user via smartphone push notification or email. Email notifications are also sent using smtplib.

[0559] Specific examples

[0560] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0561] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0562] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0563] Finally, the server sends a notification containing this security risk information to the user's smartphone at the appropriate time, informing them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0564] Prompt example

[0565] "When you enter today's events (such as 'Set up VPN') in the Secure Diary app, you will be notified of the latest applicable security advisory information. Get security information about VPNs."

[0566] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0567] Step 1: Crawling for security information using data collection methods

[0568] The server periodically crawls websites that provide security-related information. It uses BeautifulSoup and Requests to parse the HTML of the web pages and extract sections containing security information. The server then stores the extracted data (e.g., the title, summary, and risk level of the security advisory) in a database as structured data.

[0569] Input: URL of a website with security-related information

[0570] Output: Security information stored in the database

[0571] Step 2: Enter the user's activity record using the diary entry tool

[0572] Users input their daily experiences and thoughts using a dedicated smartphone application. This input data is temporarily stored locally and then sent to the server in an appropriate format (e.g., JSON format).

[0573] Input: User's diary data (text)

[0574] Output: Diary data sent to the server (JSON format)

[0575] Step 3: Analysis by natural language processing and sentiment engine

[0576] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases, and also analyzes emotional information (positive, negative, anxious, etc.) from the user's diary data using an emotion engine.

[0577] Input: Diary data sent to the server (JSON format)

[0578] Output: Extracted keywords and sentiment information

[0579] Step 4: Data verification through security information matching

[0580] The server compares the keywords and sentiment information extracted through natural language processing with the security information stored in the database, using a search engine and database queries to produce a list of security information that matches the user's needs.

[0581] Input: Extracted keywords and sentiment information, security information stored in the database

[0582] Output: List of security information that matches the user

[0583] Step 5: Notify the user via notification delivery methods

[0584] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes the title, summary, and risk level of the security information. The device (smartphone) receives this and notifies the user via push notification or email. Email notification uses smtplib.

[0585] Input: A list of security information that matches the user

[0586] Output: Notification sent to the user (push notification or email)

[0587] Concrete examples

[0588] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0589] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0590] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0591] Finally, the server sends this security risk information to the user's smartphone at the appropriate time, notifying them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0592] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0593] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0594] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0595] [Third embodiment]

[0596] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0597] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0598] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0599] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0600] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0601] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0602] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0603] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0604] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0605] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0606] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0607] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0608] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means.

[0609] To implement this system, the server first uses a data collection tool to crawl official government and related agency websites to collect subsidy information. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. The collected data (e.g., subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0610] Users enter diary data through a dedicated app or web interface for entering one-line diary entries. This diary entry tool is responsible for sending the entered data to the server in an appropriate format (e.g., JSON format).

[0611] Once the server receives the diary data, it analyzes the diary content using natural language processing. This process uses Python libraries such as NLTK and spaCy to extract keywords and sentiment from the diary text. This allows the server to evaluate how the information obtained from the user's diary relates to subsidy and support programs.

[0612] Next, the subsidy information matching tool compares the extracted keywords and sentiment information with the subsidy information stored in the database. This matching process can use a search engine such as Elasticsearch. This creates a list of subsidies and support programs available to the user.

[0613] Finally, the notification sending means sends the list of matching subsidy information to the user's terminal, and the user receives the notification from the terminal and can check specific details and how to apply.

[0614] Specific examples

[0615] For example, suppose a server crawls a government subsidy information site on a certain Monday and finds that a new subsidy for the "Eco-Reform Support Project" has been added. This information is stored in the server's database.

[0616] That evening, the user uses the app to enter a diary entry such as, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." When this diary entry data is sent to the server, the natural language processing means extracts the keywords "renovation" and "eco" and recognizes that it matches data related to "eco-friendly renovation support projects."

[0617] The next day, detailed information about the "Eco Reform Support Project" is sent from the server to the user's terminal via the notification sending means. The user can use this information to consider applying for a subsidy.

[0618] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner, and do not miss the timing to apply.

[0619] The processing flow will be explained below.

[0620] Step 1: Data collection

[0621] The server periodically crawls official government and agency websites. It uses Python's BeautifulSoup and Scrapy to parse the HTML of the webpages and extract the grant information section. The extracted grant information (e.g., grant name, summary, application conditions, deadline, etc.) is stored in a database.

[0622] Step 2: Enter your diary entry

[0623] Users enter their daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user locally, checks the contents, encodes them into an appropriate format (e.g., JSON), and sends them to the server.

[0624] Step 3: Receiving and saving diary data

[0625] The server receives the diary data sent from the terminal and stores the diary data in a database.

[0626] Step 4: Natural Language Processing

[0627] The server periodically (e.g., every night) retrieves the stored diary data and performs natural language processing (NLP) using Python's NLTK or spaCy to extract keywords and phrases from the diary text and identify themes that the user is interested in or needs.

[0628] Step 5: Matching grant information

[0629] The server compares the keywords and themes extracted through natural language processing with the grant information stored in the database, and uses a search engine such as Elasticsearch for the matching process to list grant information that matches the user's needs.

[0630] Step 6: Prepare and send notifications

[0631] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. The server then sends the notification message and data including detailed information to the user's device.

[0632] Step 7: User Notification

[0633] The terminal decodes the subsidy information data received from the server. The terminal displays a notification to the user, which includes important information such as the name of the subsidy, a summary, application conditions, and deadline. The user can review the notification and consider applying for the subsidy based on the detailed information.

[0634] Example 1

[0635] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0636] In today's world, various types of subsidy information are scattered across the web, making it difficult to efficiently collect this information and provide appropriate information that meets users' needs. In particular, it takes a great deal of time and effort for users to find appropriate subsidy information based on the information and emotions they have gained in their daily lives. The present invention solves this problem.

[0637] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0638] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means, which enable the server to periodically crawl government and related organization websites, automatically collect and store subsidy information, match the subsidy information based on keywords extracted from the user's diary, and promptly notify the user of appropriate information to their terminal.

[0639] "Data collection means" is a system component that has the function of periodically analyzing information sources on the network and automatically collecting and storing various information.

[0640] A "diary input means" is a system component that provides an interface for a user to input text data and transmit the data to the server in an appropriate format.

[0641] A "natural language processing means" is a system component that extracts specific keywords and emotions from text data and analyzes the context based on them.

[0642] The "information matching means" is a system component that compares extracted keywords and emotional information with stored information in the database.

[0643] The "notification sending means" is a system component that has a function for notifying the user's terminal of the collation result.

[0644] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means. Implementing the present invention involves the following processes.

[0645] First, the server uses data collection tools to crawl official government and related agency websites. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. For example, it can extract information about the "Eco-Renovation Support Project" from a particular page. The extracted data (subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0646] Next, the user enters diary data through a dedicated app or web interface. This diary entry method sends the entered text data to the server in an appropriate format (e.g., JSON format). For example, if a user enters the diary entry "Today I thought about renovating my house. I'm interested in eco-friendly renovations," it will be sent to the server.

[0647] When the server receives the diary data, it analyzes the diary contents using natural language processing. This analysis process uses Python libraries such as NLTK and spaCy. Keywords and emotions are extracted from the diary text. For example, keywords such as "renovation" and "eco" are extracted, and the strength of the user's interest is determined through sentiment analysis.

[0648] Next, the server uses information matching tools to match the extracted keywords and emotion information with subsidy information stored in a database. This process can be performed using a search engine such as Elasticsearch. For example, it can confirm that the keywords "renovation" and "eco" match the subsidy information for the "Eco Renovation Support Project."

[0649] Finally, the server uses the notification sending means to send a list of applicable subsidy information to the user's device. For example, detailed information about the "Eco Reform Support Project" is sent as a notification to the user's smartphone or computer. The user receives this notification and can check the specific details and how to apply.

[0650] Specific examples

[0651] As an example, suppose a server crawls a government subsidy information website on a certain Monday and saves information about a new "Eco Renovation Support Project" in the database. That evening, a user enters a diary entry through the app, stating, "Today I thought about renovating my house. I'm interested in eco-renovations." The server receives the diary data and uses natural language processing to extract keywords such as "renovation" and "eco." As a result, it recognizes that these keywords match data related to the "Eco Renovation Support Project." The next day, the server notifies the user's device of detailed information about the "Eco Renovation Support Project" through a notification sending means. The user can use this information to consider applying for a subsidy.

[0652] Examples of prompt statements

[0653] For example, an example of a prompt for a generative AI model is, "A user has entered a one-line diary entry indicating that they are interested in subsidy programs. Please explain the process of using natural language processing technology to extract subsidy information related to the eco-renovation support project from the content and send a notification to the user."

[0654] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0655] Step 1:

[0656] The server uses a data collection method to periodically crawl information sources on the network. Specifically, it uses Python's BeautifulSoup and Scrapy to analyze the HTML structure of web pages and extract subsidy information. For example, it collects information about an "eco-renovation support project" from a government website. The input is a list of URLs for the target sites, and the output is structured data of subsidy information (name, summary, application conditions, deadline, etc.). This data is stored in a database for use in the next step.

[0657] Step 2:

[0658] A user enters a one-line diary entry through a dedicated app or web interface. This diary entry method converts the text entered by the user into JSON format and sends it to the server. For example, a user might enter, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." The input is the user's diary text, and the output is the JSON-formatted data of that text.

[0659] Step 3:

[0660] The server uses natural language processing to analyze the diary data it receives. Specifically, it uses Python's NLTK and spaCy to extract keywords and emotions from the diary text. For example, it identifies keywords such as "renovation" and "eco" and analyzes that the user is interested in eco-friendly renovations. The input is diary data in JSON format, and the output is the extracted keywords and emotion data.

[0661] Step 4:

[0662] The server uses information matching methods to match the extracted keywords and sentiment information with subsidy information in the database. Elasticsearch is used for this process. For example, it verifies that keywords such as "renovation" and "eco" match subsidy information for the "Eco Renovation Support Project." The input is keywords and sentiment information, and the output is a list of related subsidy information.

[0663] Step 5:

[0664] The server uses the notification sending means to send the relevant subsidy information to the user's terminal. This notification contains detailed information about the subsidies available to the user. For example, information about the "Eco-Reform Support Project" is sent to the user's smartphone or PC. The input is a list of relevant subsidy information, and the output is a notification sent to the user's terminal.

[0665] (Application example 1)

[0666] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0667] Previously, it was difficult for brick-and-mortar store owners and managers to efficiently obtain appropriate subsidy information. In particular, because subsidy information was scattered across government and related agency websites, there was a lack of means to quickly access the necessary information. Furthermore, there was a risk that missing important information, such as subsidy application conditions and deadlines, could have a negative impact on business operations. The present invention aims to solve these problems and provide an efficient system that enables brick-and-mortar store owners and managers to obtain appropriate subsidy information in a timely manner.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0669] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means. This allows owners and managers of brick-and-mortar stores to automatically obtain appropriate subsidy information by entering a short diary entry about their daily activities and management through an application that can be installed and used on a smartphone or tablet. Specifically, the server periodically crawls websites to store subsidy information in a database, extracts keywords and emotions from the diary entries, matches them with subsidy information, and sends notifications of relevant subsidy information to users' devices in a timely manner.

[0670] The "data collection means" refers to the means for periodically crawling websites to collect subsidy information and storing it in a database as structured data.

[0671] The "diary input means" is a means by which a user can input a short diary entry about the business status, new ideas, and capital investments through a dedicated interface, and transmit the data to the server in an appropriate format.

[0672] The "natural language processing means" is a means for extracting keywords and emotions from the user's diary and analyzing the information.

[0673] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database, and identifying relevant subsidies and support systems.

[0674] The "notification sending means" is a means for notifying the user's terminal of a list of applicable subsidy information and support systems in a timely manner and providing detailed information.

[0675] "Owners and managers of physical stores" refers to business operators of commercial facilities or service businesses, and refers to individuals or organizations that manage and operate their own stores.

[0676] "Applications installed on smartphones and tablets" are dedicated applications installed on mobile devices, and are a means for users to enter diary entries and receive notifications of subsidy information.

[0677] "Structured data" refers to a data format in which collected subsidy information is organized in a specific format (e.g., JSON, XML, etc.) and stored in a database.

[0678] "Keywords" refer to important words and phrases extracted from the text of a user's diary and are used to match with subsidy information.

[0679] "Emotion" refers to the results of analyzing the emotions and feelings contained in the text of the user's diary, and is used to evaluate the relevance to subsidy information.

[0680] The present invention provides a system that provides an application that can be installed and used by owners and managers of physical stores on smartphones or tablets to obtain appropriate subsidy information. The following hardware and software are used to implement the present invention.

[0681] 1. Data collection methods:

[0682] The server periodically crawls government and related organization websites using web crawling libraries such as BeautifulSoup and Scrapy to collect subsidy information, and stores the collected data in a database as structured data.

[0683] 2. Diary entry method:

[0684] Users use a dedicated application installed on their smartphone or tablet to enter short diary entries about their daily activities and business management. The diary data is then sent to the server in an appropriate format (e.g., JSON format).

[0685] 3. Natural Language Processing Tools:

[0686] The server uses natural language processing libraries such as spacy and NLTK to extract keywords and sentiment from the diary text. This analysis process evaluates how the information obtained from the diary relates to the grant information.

[0687] 4. Subsidy information matching method:

[0688] Elasticsearch is used as a subsidy information matching tool to compare the extracted keywords and sentiment information with subsidy information stored in a database, thereby generating a list of subsidies and support programs available to users.

[0689] 5. Notification Method:

[0690] Using KafkaProducer or similar as a notification sending method, a list of applicable subsidy information is sent to the user's device in a timely manner. The user receives the notification from their device and can check specific details and how to apply.

[0691] Adding specific examples

[0692] For example, suppose a server crawls a government subsidy information website on Monday and finds that a new subsidy for the "Eco-Renovation Support Project" has been added. This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm interested in eco-renovations." When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "eco" and recognizes that it matches the data for the "Eco-Renovation Support Project."

[0693] Example prompt sentence:

[0694] A user enters a diary entry in the app as follows:

[0695] Today I was thinking about renovating my shop. I wish there was a grant to use for the interior.

[0696] This process allows the system to notify the user of appropriate grant information (e.g., "Interior Renovation Assistance Grant").

[0697] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner.

[0698] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0699] Step 1:

[0700] Data collection

[0701] The server periodically crawls government and related agency websites using web crawling libraries such as BeautifulSoup and Scrapy. It analyzes the HTML structure of the websites it accesses and extracts grant information (e.g., grant name, summary, application conditions, deadline, etc.). The extracted data is saved as structured data (e.g., JSON format).

[0702] (Input): Website URL

[0703] (Data processing): HTML analysis, information extraction

[0704] (Output): Structured data (JSON format)

[0705] Step 2:

[0706] Database storage

[0707] The server stores the collected structured data in Elasticsearch, which then serves as a database for future searches and matching. Specifically, the data is indexed using Elasticsearch's API.

[0708] (Input): Structured data (JSON format)

[0709] (Data processing): Database indexing

[0710] (Output): Index data on Elasticsearch

[0711] Step 3:

[0712] Diary entry

[0713] Users use a dedicated application installed on their smartphones or tablets to enter short diaries about their daily activities and business status. The diaries entered by the user are sent to the server in an appropriate format (e.g., JSON format).

[0714] (Input): User's diary text

[0715] (Data processing): Text format conversion (JSON format)

[0716] (Output): Data sent to the server

[0717] Step 4:

[0718] Natural Language Processing

[0719] The server analyzes the received diary data using natural language processing tools (such as Spacy or NLTK). Through this analysis, keywords and emotional information are extracted from the diary. Specifically, important words and phrases are identified from the text and an associated emotional score is calculated.

[0720] (Input): Diary data (JSON format)

[0721] (Data processing): Text analysis, keyword extraction, sentiment analysis

[0722] (Output): Keywords and sentiment information

[0723] Step 5:

[0724] Information Matching

[0725] The server uses the extracted keywords and sentiment information to match the subsidy information stored in Elasticsearch. Specifically, it uses Elasticsearch's search function to search for subsidy information that matches the keywords and lists the most relevant subsidy information.

[0726] (Input): Keywords and emotion information

[0727] (Data processing): Information search and matching

[0728] (Output): List of grant information

[0729] Step 6:

[0730] Send notifications

[0731] The server sends the list of subsidy information to the user's device via a messaging system such as KafkaProducer. The user receives the notification on their smartphone or tablet and can check the specific subsidy information and how to apply.

[0732] (Input): Grant information list

[0733] (Data processing): Notification message generation and sending

[0734] (Output): Notification to user terminal

[0735] This series of steps enables store owners and managers to obtain the most appropriate subsidy information in a timely manner.

[0736] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0737] The present invention is a system that includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0738] Data collection methods

[0739] The server periodically crawls official government and agency websites to collect grant information. Using Python libraries such as BeautifulSoup and Scrapy, the server parses the HTML of web pages and extracts sections containing grant information. The extracted data (e.g., grant name, summary, application requirements, deadline, etc.) is stored in a database as structured data.

[0740] Diary entry method

[0741] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0742] Natural language processing tools and emotion engines

[0743] Once the diary data is received, the server performs natural language processing (NLP). Using libraries such as Python's NLTK and spaCy, it extracts keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. This emotional information is used to more fully evaluate the user's interests and themes of their needs.

[0744] Subsidy information matching method

[0745] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0746] Notification sending method

[0747] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0748] Specific examples

[0749] For example, suppose a server crawls a government subsidy information site on a certain Monday and retrieves subsidy information about a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database.

[0750] That evening, the user enters a diary entry through the app, saying, "Today I thought about renovating my house, especially looking for ways to be more environmentally friendly." In addition, the emotion engine recognizes that the user has positive feelings about this content. When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions.

[0751] Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. The notification sending means notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time based on the user's positive emotion. The user can consider applying for a subsidy based on this information.

[0752] In this way, by implementing the present invention, users can efficiently obtain appropriate subsidy information through daily input including emotional information, and will not miss the timing to apply.

[0753] The processing flow will be explained below.

[0754] Step 1: Data collection

[0755] The server periodically crawls official government and agency websites. Using crawling libraries such as Python's BeautifulSoup and Scrapy, the server parses the HTML of the webpages and extracts sections containing grant information. This information includes the grant name, summary, application requirements, deadline, etc. The extracted data is then stored in a structured format in a database.

[0756] Step 2: Enter your diary entry

[0757] Users can enter daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user, checks the content, encodes it into an appropriate format such as JSON, and sends it to the server. This process ensures smooth entry for the user.

[0758] Step 3: Receiving and saving diary data

[0759] The server receives the diary data sent from the device and stores it in a database on the server. The diary data also includes metadata necessary for further analysis, such as text content and date information.

[0760] Step 4: Natural Language Processing and Sentiment Analysis

[0761] The server performs natural language processing (NLP) on the stored diary data. Specifically, it uses Python's NLTK and spaCy libraries to extract keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. For example, from the diary entry "I'm interested in eco-friendly renovations," it extracts keywords such as "renovation" and "eco" to recognize positive emotions.

[0762] Step 5: Matching grant information

[0763] The server compares the keywords extracted by natural language processing and the emotion information extracted by the emotion engine with the subsidy information stored in the database, using a search engine such as Elasticsearch to efficiently list the most relevant subsidy information.

[0764] Step 6: Prepare and send notifications

[0765] The server then encodes the list of matching grants into an appropriate format (e.g., JSON) to notify the user of the list. This data includes important information such as the grant name, summary, application requirements, and deadline.

[0766] Step 7: User Notification

[0767] The terminal analyzes and decodes the subsidy information data received from the server. The terminal displays a notification to the user. This notification includes detailed information about the subsidy and the deadline. The user can review the notification and consider applying for the subsidy based on the detailed information. The notification sending means also optimizes the timing of the notification, taking into account the user's emotional state.

[0768] As a concrete example, suppose the server collects new subsidy information for the "Environmental Protection Eco-Renovation Support Project" on Monday. That evening, the user writes in their diary, "Today I thought about renovating my house. I'm especially looking for ways to be more environmentally friendly." The emotion engine recognizes that the user has positive feelings about this topic. The next day, a notification about the "Environmental Protection Eco-Renovation Support Project" is sent to the user's device, allowing the user to consider applying for the subsidy based on the detailed information. This series of processes allows the user to efficiently obtain subsidy information that is appropriate for them and avoid missing the timing to apply.

[0769] Example 2

[0770] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0771] Conventional subsidy information systems have had problems in that it is difficult for users to manually search for subsidy information that meets their needs or to receive notifications at the appropriate time. In addition, there is no way to obtain subsidy information that reflects the user's daily activities and interests, making it difficult to collect information efficiently.

[0772] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0773] In this invention, the server includes a data collection means, a diary input means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means, thereby enabling the provision of efficient and appropriate subsidy information based on the user's daily input and emotion information.

[0774] "Data collection means" refers to a means of crawling websites on the Internet to collect necessary information and storing it in a database as structured data.

[0775] "Diary input means" refers to a means for collecting data through an application or web interface that allows users to input their daily activities and thoughts.

[0776] The "natural language processing means" is a means for analyzing input text data and performing processing to extract keywords and phrases.

[0777] The "emotion engine means" is a means for analyzing the emotion information contained in the diary data of the user and for evaluating in detail the themes that interest and need of the user based on that information.

[0778] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database.

[0779] The "notification sending means" is a means for notifying the user's terminal of information at an appropriate time.

[0780] This invention is a system including a data collection means, a diary entry means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[0781] Data collection methods

[0782] The server periodically crawls official government and related agency websites using Python web scraping libraries such as BeautifulSoup and Scrapy. The HTML data of the crawled web pages is analyzed to extract the necessary grant information (e.g., grant name, summary, application conditions, deadline, etc.). This extracted data is stored as structured data in the server's database.

[0783] Diary entry method

[0784] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[0785] Natural language processing tools

[0786] The server uses Python libraries such as NLTK and spaCy to perform natural language processing on the received diary data, extracting keywords and phrases from the diary text.

[0787] Emotion Engine Means

[0788] The server utilizes an emotion engine to extract emotion information from the user's diary data, which is used to more precisely evaluate the user's themes of interest and needs.

[0789] Subsidy information matching method

[0790] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[0791] Notification sending method

[0792] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) to notify the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[0793] Specific examples

[0794] For example, suppose a server crawls a government subsidy information website on a Monday and retrieves subsidy information for a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm especially looking for environmentally friendly ways." The emotion engine also recognizes that the user has positive emotions about this entry. When this diary entry is sent to the server, the natural language processing unit extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions. Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. Based on the user's positive emotions, the notification sending unit notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time. The user can use this information to consider applying for a subsidy.

[0795] Prompt Sentence Examples

[0796] "Please explain how the system works to suggest appropriate grant information based on keywords extracted from the user's diary and the positive emotions associated with them."

[0797] By inputting this prompt sentence into a generative AI model, it is possible to generate an easy-to-understand explanation of the operation of the system of the present invention and the coordination of each means.

[0798] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0799] Step 1:

[0800] The server periodically crawls official government and related agency websites using data collection tools. Specifically, it uses Python's BeautifulSoup and Scrapy libraries to parse the HTML data of web pages and extract subsidy information. The input is the web page URL, and the output is subsidy information (e.g., subsidy name, summary, application conditions, deadline, etc.). The extracted subsidy information is stored in a database as structured data.

[0801] Step 2:

[0802] Users enter their daily diary entries through a dedicated application or web interface. Specifically, they enter their diary entry in a text box and press the send button. The input is the user's diary entry text, and the output is diary data encoded in JSON format. The device temporarily stores the entered diary entry data locally and sends it to the server after passing validation.

[0803] Step 3:

[0804] The server performs natural language processing (NLP) on the received diary data. Specifically, it uses Python's NLTK and spaCy libraries to tokenize the text and extract keywords and phrases. The input is the user's diary data, and the output is the extracted keywords and phrases.

[0805] Step 4:

[0806] The server uses an emotion engine to extract emotional information from the user's diary data. Specifically, it uses an emotion analysis library (e.g., TextBlob or VADER) to evaluate emotions (positive, negative, neutral). The input is the user's diary data, and the output is emotional information.

[0807] Step 5:

[0808] The server compares the keywords and emotion information extracted through natural language processing with the subsidy information stored in the database. Specifically, it uses a search engine such as Elasticsearch to submit keywords as queries and search for related subsidy information. The input is keywords and emotion information, and the output is a list of subsidy information that matches the user.

[0809] Step 6:

[0810] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. Specifically, it uses a web framework such as Flask or Django to send the data to the user in JSON format. The input is a list of subsidy information, and the output is notification data in JSON format.

[0811] Step 7:

[0812] The device displays the received notification data to the user. Specifically, it displays information to the user using push notifications or in-app pop-up notifications. The input is notification data in JSON format, and the output is the notification information displayed to the user.

[0813] These processing steps allow users to efficiently obtain appropriate subsidy information through everyday input, including emotional information, and avoid missing the timing to apply.

[0814] (Application example 2)

[0815] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0816] Conventional subsidy information presentation systems have difficulty taking into account a user's daily activities and emotions, and have difficulty providing security information tailored to specific situations at the appropriate time. As a result, users may miss necessary security information or be unable to respond to risks and suffer damage. This invention aims to more effectively support users by utilizing users' diary data and emotional information to automatically match and notify them of appropriate security information.

[0817] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0818] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a notification sending means, and a security information matching means, which enables the server to automatically extract and present appropriate security information from the user's daily activity record.

[0819] "Data collection means" refers to the means of periodically crawling the source website, collecting the necessary data, and storing it in a database.

[0820] The "diary input means" is a means for providing an interface for the user to input daily events and thoughts.

[0821] The "natural language processing means" is a means for analyzing and extracting keywords and phrases from the user's diary data.

[0822] The "emotion engine" is a means for analyzing and extracting emotional information from a user's diary data.

[0823] The "notification sending means" is a means for sending necessary notifications to the user based on the analyzed information.

[0824] The "security information matching means" is a means for matching security information based on data extracted by the natural language processing means and emotion engine.

[0825] MODE FOR CARRYING OUT THE INVENTION

[0826] This invention is a system that automatically extracts and presents appropriate security information from a user's daily activity record, and includes a data collection means, a diary input means, a natural language processing means, an emotion engine, a security information matching means, and a notification sending means.

[0827] Hardware and Software Configuration

[0828] To realize this system, the following hardware and software are used:

[0829] Server: Responsible for overall control of data collection and processing.

[0830] Smartphone: Allows users to enter diary entries and receive notifications.

[0831] Python: Implements the program across all elements.

[0832] BeautifulSoup: Web crawling is used as a means of collecting data.

[0833] Requests: Communicate with the web server.

[0834] spaCy: A natural language processing tool that performs text analysis of diary data.

[0835] smtplib: Sends emails as a means of sending notifications.

[0836] System Operation Overview

[0837] Data collection

[0838] The server periodically crawls websites that provide security-related information and collects the data. To do this, it uses BeautifulSoup and Requests to parse the HTML of web pages and extract sections that contain security information. The extracted data is stored in a database as structured data.

[0839] Diary entry

[0840] Users input their daily events and emotions using a dedicated smartphone application. This input data is temporarily stored on the device and then sent to the server in JSON format.

[0841] Natural Language Processing and Sentiment Analysis

[0842] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases. It also uses an emotion engine to analyze the emotional information expressed in the diary by the user. This allows it to evaluate the themes that interest and require the user.

[0843] Security Information Matching

[0844] The server then uses the extracted keywords and sentiment information to match security information stored in a database. This process uses a search engine and database queries, resulting in a list of security information that matches the user's needs.

[0845] Send notifications

[0846] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the security information title, summary, and risk level. The device receives this and notifies the user via smartphone push notification or email. Email notifications are also sent using smtplib.

[0847] Specific examples

[0848] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0849] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0850] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0851] Finally, the server sends a notification containing this security risk information to the user's smartphone at the appropriate time, informing them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0852] Prompt example

[0853] "When you enter today's events (such as 'Set up VPN') in the Secure Diary app, you will be notified of the latest applicable security advisory information. Get security information about VPNs."

[0854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0855] Step 1: Crawling for security information using data collection methods

[0856] The server periodically crawls websites that provide security-related information. It uses BeautifulSoup and Requests to parse the HTML of the web pages and extract sections containing security information. The server then stores the extracted data (e.g., the title, summary, and risk level of the security advisory) in a database as structured data.

[0857] Input: URL of a website with security-related information

[0858] Output: Security information stored in the database

[0859] Step 2: Enter the user's activity record using the diary entry tool

[0860] Users input their daily experiences and thoughts using a dedicated smartphone application. This input data is temporarily stored locally and then sent to the server in an appropriate format (e.g., JSON format).

[0861] Input: User's diary data (text)

[0862] Output: Diary data sent to the server (JSON format)

[0863] Step 3: Analysis by natural language processing and sentiment engine

[0864] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases, and also analyzes emotional information (positive, negative, anxious, etc.) from the user's diary data using an emotion engine.

[0865] Input: Diary data sent to the server (JSON format)

[0866] Output: Extracted keywords and sentiment information

[0867] Step 4: Data verification through security information matching

[0868] The server compares the keywords and sentiment information extracted through natural language processing with the security information stored in the database, using a search engine and database queries to produce a list of security information that matches the user's needs.

[0869] Input: Extracted keywords and sentiment information, security information stored in the database

[0870] Output: List of security information that matches the user

[0871] Step 5: Notify the user via notification delivery methods

[0872] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes the title, summary, and risk level of the security information. The device (smartphone) receives this and notifies the user via push notification or email. Email notification uses smtplib.

[0873] Input: A list of security information that matches the user

[0874] Output: Notification sent to the user (push notification or email)

[0875] Concrete examples

[0876] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[0877] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[0878] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[0879] Finally, the server sends this security risk information to the user's smartphone at the appropriate time, notifying them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[0880] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0881] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0882] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0883] [Fourth embodiment]

[0884] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0885] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0886] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0887] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0888] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0889] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0890] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0891] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0892] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0893] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0894] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0895] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0896] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0897] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means.

[0898] To implement this system, the server first uses a data collection tool to crawl official government and related agency websites to collect subsidy information. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. The collected data (e.g., subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0899] Users enter diary data through a dedicated app or web interface for entering one-line diary entries. This diary entry tool is responsible for sending the entered data to the server in an appropriate format (e.g., JSON format).

[0900] Once the server receives the diary data, it analyzes the diary content using natural language processing. This process uses Python libraries such as NLTK and spaCy to extract keywords and sentiment from the diary text. This allows the server to evaluate how the information obtained from the user's diary relates to subsidy and support programs.

[0901] Next, the subsidy information matching tool compares the extracted keywords and sentiment information with the subsidy information stored in the database. This matching process can use a search engine such as Elasticsearch. This creates a list of subsidies and support programs available to the user.

[0902] Finally, the notification sending means sends the list of matching subsidy information to the user's terminal, and the user receives the notification from the terminal and can check specific details and how to apply.

[0903] Specific examples

[0904] For example, suppose a server crawls a government subsidy information site on a certain Monday and finds that a new subsidy for the "Eco-Reform Support Project" has been added. This information is stored in the server's database.

[0905] That evening, the user uses the app to enter a diary entry such as, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." When this diary entry data is sent to the server, the natural language processing means extracts the keywords "renovation" and "eco" and recognizes that it matches data related to "eco-friendly renovation support projects."

[0906] The next day, detailed information about the "Eco Reform Support Project" is sent from the server to the user's terminal via the notification sending means. The user can use this information to consider applying for a subsidy.

[0907] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner, and do not miss the timing to apply.

[0908] The processing flow will be explained below.

[0909] Step 1: Data collection

[0910] The server periodically crawls official government and agency websites. It uses Python's BeautifulSoup and Scrapy to parse the HTML of the webpages and extract the grant information section. The extracted grant information (e.g., grant name, summary, application conditions, deadline, etc.) is stored in a database.

[0911] Step 2: Enter your diary entry

[0912] Users enter their daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user locally, checks the contents, encodes them into an appropriate format (e.g., JSON), and sends them to the server.

[0913] Step 3: Receiving and saving diary data

[0914] The server receives the diary data sent from the terminal and stores the diary data in a database.

[0915] Step 4: Natural Language Processing

[0916] The server periodically (e.g., every night) retrieves the stored diary data and performs natural language processing (NLP) using Python's NLTK or spaCy to extract keywords and phrases from the diary text and identify themes that the user is interested in or needs.

[0917] Step 5: Matching grant information

[0918] The server compares the keywords and themes extracted through natural language processing with the grant information stored in the database, and uses a search engine such as Elasticsearch for the matching process to list grant information that matches the user's needs.

[0919] Step 6: Prepare and send notifications

[0920] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. The server then sends the notification message and data including detailed information to the user's device.

[0921] Step 7: User Notification

[0922] The terminal decodes the subsidy information data received from the server. The terminal displays a notification to the user, which includes important information such as the name of the subsidy, a summary, application conditions, and deadline. The user can review the notification and consider applying for the subsidy based on the detailed information.

[0923] Example 1

[0924] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0925] In today's world, various types of subsidy information are scattered across the web, making it difficult to efficiently collect this information and provide appropriate information that meets users' needs. In particular, it takes a great deal of time and effort for users to find appropriate subsidy information based on the information and emotions they have gained in their daily lives. The present invention solves this problem.

[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0927] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means, which enable the server to periodically crawl government and related organization websites, automatically collect and store subsidy information, match the subsidy information based on keywords extracted from the user's diary, and promptly notify the user of appropriate information to their terminal.

[0928] "Data collection means" is a system component that has the function of periodically analyzing information sources on the network and automatically collecting and storing various information.

[0929] A "diary input means" is a system component that provides an interface for a user to input text data and transmit the data to the server in an appropriate format.

[0930] A "natural language processing means" is a system component that extracts specific keywords and emotions from text data and analyzes the context based on them.

[0931] The "information matching means" is a system component that compares extracted keywords and emotional information with stored information in the database.

[0932] The "notification sending means" is a system component that has a function for notifying the user's terminal of the collation result.

[0933] The present invention is a system including a data collection means, a diary entry means, a natural language processing means, an information matching means, and a notification sending means. Implementing the present invention involves the following processes.

[0934] First, the server uses data collection tools to crawl official government and related agency websites. It uses Python libraries such as BeautifulSoup and Scrapy to parse the HTML of web pages and extract sections containing subsidy information. For example, it can extract information about the "Eco-Renovation Support Project" from a particular page. The extracted data (subsidy name, summary, application requirements, deadline, etc.) is then stored in a database as structured data.

[0935] Next, the user enters diary data through a dedicated app or web interface. This diary entry method sends the entered text data to the server in an appropriate format (e.g., JSON format). For example, if a user enters the diary entry "Today I thought about renovating my house. I'm interested in eco-friendly renovations," it will be sent to the server.

[0936] When the server receives the diary data, it analyzes the diary contents using natural language processing. This analysis process uses Python libraries such as NLTK and spaCy. Keywords and emotions are extracted from the diary text. For example, keywords such as "renovation" and "eco" are extracted, and the strength of the user's interest is determined through sentiment analysis.

[0937] Next, the server uses information matching tools to match the extracted keywords and emotion information with subsidy information stored in a database. This process can be performed using a search engine such as Elasticsearch. For example, it can confirm that the keywords "renovation" and "eco" match the subsidy information for the "Eco Renovation Support Project."

[0938] Finally, the server uses the notification sending means to send a list of applicable subsidy information to the user's device. For example, detailed information about the "Eco Reform Support Project" is sent as a notification to the user's smartphone or computer. The user receives this notification and can check the specific details and how to apply.

[0939] Specific examples

[0940] As an example, suppose a server crawls a government subsidy information website on a certain Monday and saves information about a new "Eco Renovation Support Project" in the database. That evening, a user enters a diary entry through the app, stating, "Today I thought about renovating my house. I'm interested in eco-renovations." The server receives the diary data and uses natural language processing to extract keywords such as "renovation" and "eco." As a result, it recognizes that these keywords match data related to the "Eco Renovation Support Project." The next day, the server notifies the user's device of detailed information about the "Eco Renovation Support Project" through a notification sending means. The user can use this information to consider applying for a subsidy.

[0941] Examples of prompt statements

[0942] For example, an example of a prompt for a generative AI model is, "A user has entered a one-line diary entry indicating that they are interested in subsidy programs. Please explain the process of using natural language processing technology to extract subsidy information related to the eco-renovation support project from the content and send a notification to the user."

[0943] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0944] Step 1:

[0945] The server uses a data collection method to periodically crawl information sources on the network. Specifically, it uses Python's BeautifulSoup and Scrapy to analyze the HTML structure of web pages and extract subsidy information. For example, it collects information about an "eco-renovation support project" from a government website. The input is a list of URLs for the target sites, and the output is structured data of subsidy information (name, summary, application conditions, deadline, etc.). This data is stored in a database for use in the next step.

[0946] Step 2:

[0947] A user enters a one-line diary entry through a dedicated app or web interface. This diary entry method converts the text entered by the user into JSON format and sends it to the server. For example, a user might enter, "Today I thought about renovating my house. I'm interested in eco-friendly renovations." The input is the user's diary text, and the output is the JSON-formatted data of that text.

[0948] Step 3:

[0949] The server uses natural language processing to analyze the diary data it receives. Specifically, it uses Python's NLTK and spaCy to extract keywords and emotions from the diary text. For example, it identifies keywords such as "renovation" and "eco" and analyzes that the user is interested in eco-friendly renovations. The input is diary data in JSON format, and the output is the extracted keywords and emotion data.

[0950] Step 4:

[0951] The server uses information matching methods to match the extracted keywords and sentiment information with subsidy information in the database. Elasticsearch is used for this process. For example, it verifies that keywords such as "renovation" and "eco" match subsidy information for the "Eco Renovation Support Project." The input is keywords and sentiment information, and the output is a list of related subsidy information.

[0952] Step 5:

[0953] The server uses the notification sending means to send the relevant subsidy information to the user's terminal. This notification contains detailed information about the subsidies available to the user. For example, information about the "Eco-Reform Support Project" is sent to the user's smartphone or PC. The input is a list of relevant subsidy information, and the output is a notification sent to the user's terminal.

[0954] (Application example 1)

[0955] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0956] Previously, it was difficult for brick-and-mortar store owners and managers to efficiently obtain appropriate subsidy information. In particular, because subsidy information was scattered across government and related agency websites, there was a lack of means to quickly access the necessary information. Furthermore, there was a risk that missing important information, such as subsidy application conditions and deadlines, could have a negative impact on business operations. The present invention aims to solve these problems and provide an efficient system that enables brick-and-mortar store owners and managers to obtain appropriate subsidy information in a timely manner.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0958] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, a subsidy information matching means, and a notification sending means. This allows owners and managers of brick-and-mortar stores to automatically obtain appropriate subsidy information by entering a short diary entry about their daily activities and management through an application that can be installed and used on a smartphone or tablet. Specifically, the server periodically crawls websites to store subsidy information in a database, extracts keywords and emotions from the diary entries, matches them with subsidy information, and sends notifications of relevant subsidy information to users' devices in a timely manner.

[0959] The "data collection means" refers to the means for periodically crawling websites to collect subsidy information and storing it in a database as structured data.

[0960] The "diary input means" is a means by which a user can input a short diary entry about the business status, new ideas, and capital investments through a dedicated interface, and transmit the data to the server in an appropriate format.

[0961] The "natural language processing means" is a means for extracting keywords and emotions from the user's diary and analyzing the information.

[0962] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database, and identifying relevant subsidies and support systems.

[0963] The "notification sending means" is a means for notifying the user's terminal of a list of applicable subsidy information and support systems in a timely manner and providing detailed information.

[0964] "Owners and managers of physical stores" refers to business operators of commercial facilities or service businesses, and refers to individuals or organizations that manage and operate their own stores.

[0965] "Applications installed on smartphones and tablets" are dedicated applications installed on mobile devices, and are a means for users to enter diary entries and receive notifications of subsidy information.

[0966] "Structured data" refers to a data format in which collected subsidy information is organized in a specific format (e.g., JSON, XML, etc.) and stored in a database.

[0967] "Keywords" refer to important words and phrases extracted from the text of a user's diary and are used to match with subsidy information.

[0968] "Emotion" refers to the results of analyzing the emotions and feelings contained in the text of the user's diary, and is used to evaluate the relevance to subsidy information.

[0969] The present invention provides a system that provides an application that can be installed and used by owners and managers of physical stores on smartphones or tablets to obtain appropriate subsidy information. The following hardware and software are used to implement the present invention.

[0970] 1. Data collection methods:

[0971] The server periodically crawls government and related organization websites using web crawling libraries such as BeautifulSoup and Scrapy to collect subsidy information, and stores the collected data in a database as structured data.

[0972] 2. Diary entry method:

[0973] Users use a dedicated application installed on their smartphone or tablet to enter short diary entries about their daily activities and business management. The diary data is then sent to the server in an appropriate format (e.g., JSON format).

[0974] 3. Natural Language Processing Tools:

[0975] The server uses natural language processing libraries such as spacy and NLTK to extract keywords and sentiment from the diary text. This analysis process evaluates how the information obtained from the diary relates to the grant information.

[0976] 4. Subsidy information matching method:

[0977] Elasticsearch is used as a subsidy information matching tool to compare the extracted keywords and sentiment information with subsidy information stored in a database, thereby generating a list of subsidies and support programs available to users.

[0978] 5. Notification Method:

[0979] Using KafkaProducer or similar as a notification sending method, a list of applicable subsidy information is sent to the user's device in a timely manner. The user receives the notification from their device and can check specific details and how to apply.

[0980] Adding specific examples

[0981] For example, suppose a server crawls a government subsidy information website on Monday and finds that a new subsidy for the "Eco-Renovation Support Project" has been added. This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm interested in eco-renovations." When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "eco" and recognizes that it matches the data for the "Eco-Renovation Support Project."

[0982] Example prompt sentence:

[0983] A user enters a diary entry in the app as follows:

[0984] Today I was thinking about renovating my shop. I wish there was a grant to use for the interior.

[0985] This process allows the system to notify the user of appropriate grant information (e.g., "Interior Renovation Assistance Grant").

[0986] In this way, by implementing the present invention, users can obtain appropriate subsidy information in a timely and efficient manner.

[0987] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0988] Step 1:

[0989] Data collection

[0990] The server periodically crawls government and related agency websites using web crawling libraries such as BeautifulSoup and Scrapy. It analyzes the HTML structure of the websites it accesses and extracts grant information (e.g., grant name, summary, application conditions, deadline, etc.). The extracted data is saved as structured data (e.g., JSON format).

[0991] (Input): Website URL

[0992] (Data processing): HTML analysis, information extraction

[0993] (Output): Structured data (JSON format)

[0994] Step 2:

[0995] Database storage

[0996] The server stores the collected structured data in Elasticsearch, which then serves as a database for future searches and matching. Specifically, the data is indexed using Elasticsearch's API.

[0997] (Input): Structured data (JSON format)

[0998] (Data processing): Database indexing

[0999] (Output): Index data on Elasticsearch

[1000] Step 3:

[1001] Diary entry

[1002] Users use a dedicated application installed on their smartphones or tablets to enter short diaries about their daily activities and business status. The diaries entered by the user are sent to the server in an appropriate format (e.g., JSON format).

[1003] (Input): User's diary text

[1004] (Data processing): Text format conversion (JSON format)

[1005] (Output): Data sent to the server

[1006] Step 4:

[1007] Natural Language Processing

[1008] The server analyzes the received diary data using natural language processing tools (such as Spacy or NLTK). Through this analysis, keywords and emotional information are extracted from the diary. Specifically, important words and phrases are identified from the text and an associated emotional score is calculated.

[1009] (Input): Diary data (JSON format)

[1010] (Data processing): Text analysis, keyword extraction, sentiment analysis

[1011] (Output): Keywords and sentiment information

[1012] Step 5:

[1013] Information Matching

[1014] The server uses the extracted keywords and sentiment information to match the subsidy information stored in Elasticsearch. Specifically, it uses Elasticsearch's search function to search for subsidy information that matches the keywords and lists the most relevant subsidy information.

[1015] (Input): Keywords and emotion information

[1016] (Data processing): Information search and matching

[1017] (Output): List of grant information

[1018] Step 6:

[1019] Send notifications

[1020] The server sends the list of subsidy information to the user's device via a messaging system such as KafkaProducer. The user receives the notification on their smartphone or tablet and can check the specific subsidy information and how to apply.

[1021] (Input): Grant information list

[1022] (Data processing): Notification message generation and sending

[1023] (Output): Notification to user terminal

[1024] This series of steps enables store owners and managers to obtain the most appropriate subsidy information in a timely manner.

[1025] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1026] The present invention is a system that includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[1027] Data collection methods

[1028] The server periodically crawls official government and agency websites to collect grant information. Using Python libraries such as BeautifulSoup and Scrapy, the server parses the HTML of web pages and extracts sections containing grant information. The extracted data (e.g., grant name, summary, application requirements, deadline, etc.) is stored in a database as structured data.

[1029] Diary entry method

[1030] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[1031] Natural language processing tools and emotion engines

[1032] Once the diary data is received, the server performs natural language processing (NLP). Using libraries such as Python's NLTK and spaCy, it extracts keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. This emotional information is used to more fully evaluate the user's interests and themes of their needs.

[1033] Subsidy information matching method

[1034] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[1035] Notification sending method

[1036] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[1037] Specific examples

[1038] For example, suppose a server crawls a government subsidy information site on a certain Monday and retrieves subsidy information about a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database.

[1039] That evening, the user enters a diary entry through the app, saying, "Today I thought about renovating my house, especially looking for ways to be more environmentally friendly." In addition, the emotion engine recognizes that the user has positive feelings about this content. When this diary data is sent to the server, the natural language processing means extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions.

[1040] Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. The notification sending means notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time based on the user's positive emotion. The user can consider applying for a subsidy based on this information.

[1041] In this way, by implementing the present invention, users can efficiently obtain appropriate subsidy information through daily input including emotional information, and will not miss the timing to apply.

[1042] The processing flow will be explained below.

[1043] Step 1: Data collection

[1044] The server periodically crawls official government and agency websites. Using crawling libraries such as Python's BeautifulSoup and Scrapy, the server parses the HTML of the webpages and extracts sections containing grant information. This information includes the grant name, summary, application requirements, deadline, etc. The extracted data is then stored in a structured format in a database.

[1045] Step 2: Enter your diary entry

[1046] Users can enter daily diary entries through a dedicated app or web interface. The device temporarily stores the diary data entered by the user, checks the content, encodes it into an appropriate format such as JSON, and sends it to the server. This process ensures smooth entry for the user.

[1047] Step 3: Receiving and saving diary data

[1048] The server receives the diary data sent from the device and stores it in a database on the server. The diary data also includes metadata necessary for further analysis, such as text content and date information.

[1049] Step 4: Natural Language Processing and Sentiment Analysis

[1050] The server performs natural language processing (NLP) on the stored diary data. Specifically, it uses Python's NLTK and spaCy libraries to extract keywords and phrases from the diary text. It also uses an emotion engine to extract emotional information from the user's diary. For example, from the diary entry "I'm interested in eco-friendly renovations," it extracts keywords such as "renovation" and "eco" to recognize positive emotions.

[1051] Step 5: Matching grant information

[1052] The server compares the keywords extracted by natural language processing and the emotion information extracted by the emotion engine with the subsidy information stored in the database, using a search engine such as Elasticsearch to efficiently list the most relevant subsidy information.

[1053] Step 6: Prepare and send notifications

[1054] The server then encodes the list of matching grants into an appropriate format (e.g., JSON) to notify the user of the list. This data includes important information such as the grant name, summary, application requirements, and deadline.

[1055] Step 7: User Notification

[1056] The terminal analyzes and decodes the subsidy information data received from the server. The terminal displays a notification to the user. This notification includes detailed information about the subsidy and the deadline. The user can review the notification and consider applying for the subsidy based on the detailed information. The notification sending means also optimizes the timing of the notification, taking into account the user's emotional state.

[1057] As a concrete example, suppose the server collects new subsidy information for the "Environmental Protection Eco-Renovation Support Project" on Monday. That evening, the user writes in their diary, "Today I thought about renovating my house. I'm especially looking for ways to be more environmentally friendly." The emotion engine recognizes that the user has positive feelings about this topic. The next day, a notification about the "Environmental Protection Eco-Renovation Support Project" is sent to the user's device, allowing the user to consider applying for the subsidy based on the detailed information. This series of processes allows the user to efficiently obtain subsidy information that is appropriate for them and avoid missing the timing to apply.

[1058] Example 2

[1059] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1060] Conventional subsidy information systems have had problems in that it is difficult for users to manually search for subsidy information that meets their needs or to receive notifications at the appropriate time. In addition, there is no way to obtain subsidy information that reflects the user's daily activities and interests, making it difficult to collect information efficiently.

[1061] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1062] In this invention, the server includes a data collection means, a diary input means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means, thereby enabling the provision of efficient and appropriate subsidy information based on the user's daily input and emotion information.

[1063] "Data collection means" refers to a means of crawling websites on the Internet to collect necessary information and storing it in a database as structured data.

[1064] "Diary input means" refers to a means for collecting data through an application or web interface that allows users to input their daily activities and thoughts.

[1065] The "natural language processing means" is a means for analyzing input text data and performing processing to extract keywords and phrases.

[1066] The "emotion engine means" is a means for analyzing the emotion information contained in the diary data of the user and for evaluating in detail the themes that interest and need of the user based on that information.

[1067] The "subsidy information matching means" is a means for matching the extracted keywords and emotion information with subsidy information stored in a database.

[1068] The "notification sending means" is a means for notifying the user's terminal of information at an appropriate time.

[1069] This invention is a system including a data collection means, a diary entry means, a natural language processing means, an emotion engine means, a subsidy information matching means, and a notification sending means. This system automatically extracts and presents appropriate subsidy information from a user's daily activity record.

[1070] Data collection methods

[1071] The server periodically crawls official government and related agency websites using Python web scraping libraries such as BeautifulSoup and Scrapy. The HTML data of the crawled web pages is analyzed to extract the necessary grant information (e.g., grant name, summary, application conditions, deadline, etc.). This extracted data is stored as structured data in the server's database.

[1072] Diary entry method

[1073] Users enter daily diary entries through a dedicated application or a web interface. The device temporarily stores the diary data entered by the user locally, checks the input, encodes it into an appropriate format (e.g., JSON format), and sends it to the server.

[1074] Natural language processing tools

[1075] The server uses Python libraries such as NLTK and spaCy to perform natural language processing on the received diary data, extracting keywords and phrases from the diary text.

[1076] Emotion Engine Means

[1077] The server utilizes an emotion engine to extract emotion information from the user's diary data, which is used to more precisely evaluate the user's themes of interest and needs.

[1078] Subsidy information matching method

[1079] The server compares the keywords and sentiment information extracted through natural language processing with the subsidy information stored in the database, using a search engine such as Elasticsearch to produce a list of subsidy information that matches the user's needs.

[1080] Notification sending method

[1081] The server encodes the list of matching grant information into an appropriate format (e.g., JSON format) to notify the user. The notification includes important information such as the grant name, summary, application conditions, and deadline. The terminal receives the notification and displays it to the user. The notification sending means is configured to send the notification at the optimal timing, taking into account the user's emotional state.

[1082] Specific examples

[1083] For example, suppose a server crawls a government subsidy information website on a Monday and retrieves subsidy information for a new "Environmental Protection Eco-Renovation Support Project." This information is stored in the server's database. That evening, a user enters a diary entry through the app: "Today I thought about renovating my house. I'm especially looking for environmentally friendly ways." The emotion engine also recognizes that the user has positive emotions about this entry. When this diary entry is sent to the server, the natural language processing unit extracts keywords such as "renovation" and "environment," and the emotion engine detects positive emotions. Based on the extracted keywords and emotion information, the server determines that the "Environmental Protection Eco-Renovation Support Project" meets the user's needs and lists related information. Based on the user's positive emotions, the notification sending unit notifies the user's device of detailed information about the "Environmental Protection Eco-Renovation Support Project" at an appropriate time. The user can use this information to consider applying for a subsidy.

[1084] Prompt Sentence Examples

[1085] "Please explain how the system works to suggest appropriate grant information based on keywords extracted from the user's diary and the positive emotions associated with them."

[1086] By inputting this prompt sentence into a generative AI model, it is possible to generate an easy-to-understand explanation of the operation of the system of the present invention and the coordination of each means.

[1087] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1088] Step 1:

[1089] The server periodically crawls official government and related agency websites using data collection tools. Specifically, it uses Python's BeautifulSoup and Scrapy libraries to parse the HTML data of web pages and extract subsidy information. The input is the web page URL, and the output is subsidy information (e.g., subsidy name, summary, application conditions, deadline, etc.). The extracted subsidy information is stored in a database as structured data.

[1090] Step 2:

[1091] Users enter their daily diary entries through a dedicated application or web interface. Specifically, they enter their diary entry in a text box and press the send button. The input is the user's diary entry text, and the output is diary data encoded in JSON format. The device temporarily stores the entered diary entry data locally and sends it to the server after passing validation.

[1092] Step 3:

[1093] The server performs natural language processing (NLP) on the received diary data. Specifically, it uses Python's NLTK and spaCy libraries to tokenize the text and extract keywords and phrases. The input is the user's diary data, and the output is the extracted keywords and phrases.

[1094] Step 4:

[1095] The server uses an emotion engine to extract emotional information from the user's diary data. Specifically, it uses an emotion analysis library (e.g., TextBlob or VADER) to evaluate emotions (positive, negative, neutral). The input is the user's diary data, and the output is emotional information.

[1096] Step 5:

[1097] The server compares the keywords and emotion information extracted through natural language processing with the subsidy information stored in the database. Specifically, it uses a search engine such as Elasticsearch to submit keywords as queries and search for related subsidy information. The input is keywords and emotion information, and the output is a list of subsidy information that matches the user.

[1098] Step 6:

[1099] The server encodes the list of matching subsidy information into an appropriate format (e.g., JSON format) to notify the user. Specifically, it uses a web framework such as Flask or Django to send the data to the user in JSON format. The input is a list of subsidy information, and the output is notification data in JSON format.

[1100] Step 7:

[1101] The device displays the received notification data to the user. Specifically, it displays information to the user using push notifications or in-app pop-up notifications. The input is notification data in JSON format, and the output is the notification information displayed to the user.

[1102] These processing steps allow users to efficiently obtain appropriate subsidy information through everyday input, including emotional information, and avoid missing the timing to apply.

[1103] (Application example 2)

[1104] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1105] Conventional subsidy information presentation systems have difficulty taking into account a user's daily activities and emotions, and have difficulty providing security information tailored to specific situations at the appropriate time. As a result, users may miss necessary security information or be unable to respond to risks and suffer damage. This invention aims to more effectively support users by utilizing users' diary data and emotional information to automatically match and notify them of appropriate security information.

[1106] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1107] In this invention, the server includes a data collection means, a diary entry means, a natural language processing means, an emotion engine, a notification sending means, and a security information matching means, which enables the server to automatically extract and present appropriate security information from the user's daily activity record.

[1108] "Data collection means" refers to the means of periodically crawling the source website, collecting the necessary data, and storing it in a database.

[1109] The "diary input means" is a means for providing an interface for the user to input daily events and thoughts.

[1110] The "natural language processing means" is a means for analyzing and extracting keywords and phrases from the user's diary data.

[1111] The "emotion engine" is a means for analyzing and extracting emotional information from a user's diary data.

[1112] The "notification sending means" is a means for sending necessary notifications to the user based on the analyzed information.

[1113] The "security information matching means" is a means for matching security information based on data extracted by the natural language processing means and emotion engine.

[1114] MODE FOR CARRYING OUT THE INVENTION

[1115] This invention is a system that automatically extracts and presents appropriate security information from a user's daily activity record, and includes a data collection means, a diary input means, a natural language processing means, an emotion engine, a security information matching means, and a notification sending means.

[1116] Hardware and Software Configuration

[1117] To realize this system, the following hardware and software are used:

[1118] Server: Responsible for overall control of data collection and processing.

[1119] Smartphone: Allows users to enter diary entries and receive notifications.

[1120] Python: Implements the program across all elements.

[1121] BeautifulSoup: Web crawling is used as a means of collecting data.

[1122] Requests: Communicate with the web server.

[1123] spaCy: A natural language processing tool that performs text analysis of diary data.

[1124] smtplib: Sends emails as a means of sending notifications.

[1125] System Operation Overview

[1126] Data collection

[1127] The server periodically crawls websites that provide security-related information and collects the data. To do this, it uses BeautifulSoup and Requests to parse the HTML of web pages and extract sections that contain security information. The extracted data is stored in a database as structured data.

[1128] Diary entry

[1129] Users input their daily events and emotions using a dedicated smartphone application. This input data is temporarily stored on the device and then sent to the server in JSON format.

[1130] Natural Language Processing and Sentiment Analysis

[1131] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases. It also uses an emotion engine to analyze the emotional information expressed in the diary by the user. This allows it to evaluate the themes that interest and require the user.

[1132] Security Information Matching

[1133] The server then uses the extracted keywords and sentiment information to match security information stored in a database. This process uses a search engine and database queries, resulting in a list of security information that matches the user's needs.

[1134] Send notifications

[1135] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes important information such as the security information title, summary, and risk level. The device receives this and notifies the user via smartphone push notification or email. Email notifications are also sent using smtplib.

[1136] Specific examples

[1137] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[1138] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[1139] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[1140] Finally, the server sends a notification containing this security risk information to the user's smartphone at the appropriate time, informing them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[1141] Prompt example

[1142] "When you enter today's events (such as 'Set up VPN') in the Secure Diary app, you will be notified of the latest applicable security advisory information. Get security information about VPNs."

[1143] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1144] Step 1: Crawling for security information using data collection methods

[1145] The server periodically crawls websites that provide security-related information. It uses BeautifulSoup and Requests to parse the HTML of the web pages and extract sections containing security information. The server then stores the extracted data (e.g., the title, summary, and risk level of the security advisory) in a database as structured data.

[1146] Input: URL of a website with security-related information

[1147] Output: Security information stored in the database

[1148] Step 2: Enter the user's activity record using the diary entry tool

[1149] Users input their daily experiences and thoughts using a dedicated smartphone application. This input data is temporarily stored locally and then sent to the server in an appropriate format (e.g., JSON format).

[1150] Input: User's diary data (text)

[1151] Output: Diary data sent to the server (JSON format)

[1152] Step 3: Analysis by natural language processing and sentiment engine

[1153] The server analyzes the received diary data using a natural language processing library (spaCy) to extract key keywords and phrases, and also analyzes emotional information (positive, negative, anxious, etc.) from the user's diary data using an emotion engine.

[1154] Input: Diary data sent to the server (JSON format)

[1155] Output: Extracted keywords and sentiment information

[1156] Step 4: Data verification through security information matching

[1157] The server compares the keywords and sentiment information extracted through natural language processing with the security information stored in the database, using a search engine and database queries to produce a list of security information that matches the user's needs.

[1158] Input: Extracted keywords and sentiment information, security information stored in the database

[1159] Output: List of security information that matches the user

[1160] Step 5: Notify the user via notification delivery methods

[1161] The server encodes the list of matching security information into an appropriate format (e.g., JSON format) for notification to the user. The notification includes the title, summary, and risk level of the security information. The device (smartphone) receives this and notifies the user via push notification or email. Email notification uses smtplib.

[1162] Input: A list of security information that matches the user

[1163] Output: Notification sent to the user (push notification or email)

[1164] Concrete examples

[1165] For example, suppose a server crawls a security information site on a certain day and obtains new information about "VPN configuration security risks." This information is stored in the server's database.

[1166] That evening, the user enters a diary entry on their smartphone application stating, "I set up a VPN today, but I'm worried." The server receives this diary entry, extracts the keyword "VPN," and uses its emotion engine to recognize that the user is worried about security.

[1167] Based on these keywords and emotional information, the server determines that the information on "VPN configuration security risks" meets the user's needs and adds the information to the notification list.

[1168] Finally, the server sends this security risk information to the user's smartphone at the appropriate time, notifying them that "There is a new VPN security risk. Please see here for details." The user can then take security measures based on this information.

[1169] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1170] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1171] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1172] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1173] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1174] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1175] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1177] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1178] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1179] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1180] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1181] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1182] 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.

[1183] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1184] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1185] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1186] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1187] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1188] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1189] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1190] The following is further disclosed regarding the above embodiment.

[1191] (Claim 1)

[1192] data collection means;

[1193] A diary input means;

[1194] natural language processing means;

[1195] A subsidy information matching means;

[1196] A notification sending means;

[1197] A system including:

[1198] (Claim 2)

[1199] 2. The system of claim 1, wherein the data collection means is configured to periodically crawl websites and store grant information in a database.

[1200] (Claim 3)

[1201] 2. The system according to claim 1, wherein the natural language processing means is configured to extract keywords from the diary and match them with the subsidy information.

[1202] "Example 1"

[1203] (Claim 1)

[1204] data collection means;

[1205] A diary input means;

[1206] natural language processing means;

[1207] an information matching means;

[1208] A notification sending means;

[1209] A system including:

[1210] (Claim 2)

[1211] 10. The system of claim 1, wherein the data collection means is configured to periodically analyze the network resources and store the information in a database.

[1212] (Claim 3)

[1213] 2. The system of claim 1, wherein the natural language processing means is configured to extract target terms from the text data and match them with the information.

[1214] "Application Example 1"

[1215] (Claim 1)

[1216] data collection means;

[1217] A diary input means;

[1218] natural language processing means;

[1219] A subsidy information matching means;

[1220] A notification sending means;

[1221] A system including:

[1222] (Claim 2)

[1223] 2. The system of claim 1, wherein the data collection means is configured to periodically crawl websites and store the grant information in a database as structured data.

[1224] (Claim 3)

[1225] 2. The system of claim 1, wherein the natural language processing means is configured to extract keywords and sentiments from the diary and match them with the grant information.

[1226] (Claim 4)

[1227] 2. The system of claim 1, wherein the notification sending means is configured to send notifications of relevant subsidy information to the user's terminal in a timely manner.

[1228] (Claim 5)

[1229] The system of claim 1, wherein the system includes an application intended for use by owners or managers of physical stores by installing it on smartphones or tablets.

[1230] (Claim 6)

[1231] 2. The system according to claim 1, wherein the diary entry means is configured to provide a dedicated interface for entering one-line diary entries relating to business conditions, new ideas, and capital investments.

[1232] "Example 2: Combining Emotion Engines"

[1233] (Claim 1)

[1234] data collection means;

[1235] A diary input means;

[1236] natural language processing means;

[1237] an emotion engine means;

[1238] A subsidy information matching means;

[1239] A notification sending means;

[1240] A system including:

[1241] (Claim 2)

[1242] 2. The system of claim 1, wherein the data collection means is configured to periodically crawl websites and store grant information in a database.

[1243] (Claim 3)

[1244] 2. The system according to claim 1, wherein the natural language processing means is configured to extract keywords from the diary and match them with the subsidy information together with the emotion information extracted by the emotion engine.

[1245] "Application example 2 when combining emotion engines"

[1246] (Claim 1)

[1247] data collection means;

[1248] A diary input means;

[1249] natural language processing means;

[1250] Emotion engine and

[1251] A notification sending means;

[1252] security information matching means;

[1253] A system including:

[1254] (Claim 2)

[1255] 10. The system of claim 1, wherein the data collection means is configured to periodically crawl the information source and store the security information in a database.

[1256] (Claim 3)

[1257] 2. The system of claim 1, wherein the natural language processing means is configured to extract keywords from the diary and match them with security information. [Explanation of symbols]

[1258] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] a data collection method that periodically crawls websites and stores grant information in a database; a diary input means for receiving diary data input by a user; A natural language processing means for extracting keywords from the user's diary and identifying themes that interest or require the user based on the keywords; a subsidy information matching means for matching the extracted keywords with subsidy information in a database and listing matching subsidy information; a notification sending means for notifying a user terminal of the applicable subsidy information; A system including:

Images