system

Abstract

Provide a system. [Solution] A means of entering the business name, industry, and other necessary information; means for converting input information into a data format and transmitting the data; a means of collecting data on grant information and competitor activity; A means of analyzing the collected data and generating proposal ideas; A means for displaying a list of generated proposal ideas; a means for setting detailed search criteria for the proposed ideas; A means for performing further detailed analysis based on the search criteria set; A means to display specific timeframes, estimated amounts, and profitability; 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] Modern companies need to constantly seek out new business ideas to efficiently manage a wide range of operations and beat competitors. However, finding effective and profitable proposals requires collecting and analyzing a huge amount of data, a process that takes a lot of time and effort. In particular, properly understanding information on subsidy businesses and competitor trends, and generating specific proposals based on that information, requires specialized knowledge and skills, making it a major challenge for many companies. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including: a means for inputting a business name, industry, and other necessary information; a means for converting the input information into a data format and transmitting it; a means for collecting data on subsidy information and competitor trends; a means for analyzing the collected data and generating proposal ideas; a means for displaying a list of the generated proposal ideas; a means for setting detailed search conditions for the proposal ideas; a means for performing further detailed analysis based on the set search conditions; and a means for displaying specific time periods, estimated amounts, and profitability. This system enables companies to efficiently and effectively obtain profitable proposal ideas and improve their competitiveness. As such, this system can become an important tool in the modern business environment.

[0006] "Business name" is the name of the company or corporation that is the subject of the proposed idea.

[0007] "Industry" is a category that indicates the main business content or field of activity of a business operator.

[0008] "Requirements" refers to any additional information or conditions necessary to generate a Proposal Idea, including specific details other than the business name and industry.

[0009] "Data format" refers to a format in which information is converted into a form that is easy for a computer to process, and includes formats such as JSON and XML.

[0010] "Grant Information" means information about financial assistance provided by governments and other organizations, including details of grants available to businesses and operators.

[0011] "Competitor trends" refers to information about the activities and market movements of competitors in the same industry.

[0012] "Means of collecting data" refers to the methods and tools used to obtain the necessary information from the Internet or databases.

[0013] "Means for analyzing data" refers to methods and techniques for processing collected data and extracting useful information.

[0014] A "proposed idea" is a proposal for a new business initiative or project that is expected to be profitable.

[0015] "Means for displaying in a list" refers to a method for displaying the generated proposal ideas in a list format so that they can be visually confirmed.

[0016] "Detailed search conditions" are specific conditions used to narrow down proposed ideas and set priorities.

[0017] "Detailed analysis" is the process of obtaining more detailed information and inferences based on the set search criteria.

[0018] "Duration" refers to the range of time required to implement the proposed idea.

[0019] "Estimated amount" is the total amount of costs expected to be incurred in realizing the proposed idea.

[0020] "Profitability" refers to the potential income or profits that a proposed idea may bring. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is a system that includes a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and the trends of competitors, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability. A specific method for implementing this system is described below.

[0043] Step 1: User Input and Initial Settings

[0044] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0045] Step 2: Submit your input

[0046] The device sends the converted data format information to the server, which then prepares the data for analysis.

[0047] Step 3: Gathering grant information and competitor trends

[0048] The server collects data on the latest grant information and competitor trends from multiple sources (government grant information API, industry news sites, databases, etc.) The server efficiently obtains the required information using APIs and web scraping technology.

[0049] Step 4: Analyze the data and generate proposal ideas

[0050] The server analyzes the collected data and uses natural language processing and machine learning technologies to generate profitable proposal ideas based on the user's input, such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products."

[0051] Step 5: Listing the proposed ideas

[0052] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0053] Step 6: Setting advanced search criteria

[0054] The user selects ideas that interest them from the suggestions and sets detailed search conditions (e.g., region restrictions, budget limits, etc.). The device then sends these conditions back to the server.

[0055] Step 7: Detailed analysis

[0056] The server then performs further analysis based on the search criteria set by the user, specifically providing grant availability, budget estimates, and profitability forecasts for the selected proposal ideas.

[0057] Step 8: View detailed results

[0058] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0059] Specific examples

[0060] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. The server then analyzes this data and generates proposal ideas such as "utilizing the digitalization promotion subsidy" and "developing a cloud service for a new product." When the user selects "utilizing the digitalization promotion subsidy" and sets the detailed conditions, such as "region: Tokyo" and "maximum budget: 10 million yen," the server performs a detailed analysis based on this information and can provide information such as the specific implementation period, required budget, and projected profitability.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0064] Step 2:

[0065] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0066] Step 3:

[0067] The server receives the JSON data sent from the device and prepares it for analysis.

[0068] Step 4:

[0069] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0070] Step 5:

[0071] The server analyzes the collected data and uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input.

[0072] Step 6:

[0073] The server compiles the generated proposal ideas into a list, including ideas such as "utilizing digitalization promotion subsidies" and "developing new product cloud services."

[0074] Step 7:

[0075] The server sends the list of proposed ideas to the terminal in JSON format, ensuring data integrity and security.

[0076] Step 8:

[0077] The terminal analyzes the list of proposed ideas received from the server and visually displays them, from which the user can select the proposed ideas that interest them.

[0078] Step 9:

[0079] Users can select specific proposal ideas and set detailed search conditions, such as "Region: Tokyo" or "Budget limit: 10 million yen."

[0080] Step 10:

[0081] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0082] Step 11:

[0083] The server receives the detailed search conditions and performs further detailed analysis, including determining whether or not grants can be used based on the newly set conditions, budget estimates, and revenue forecasts.

[0084] Step 12:

[0085] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0086] Step 13:

[0087] The terminal analyzes the detailed results received from the server and visually displays them for the user to review, including specific timeframes, estimated costs, and profitability information.

[0088] In this way, users can efficiently and effectively obtain proposal ideas that are likely to generate profits.

[0089] Example 1

[0090] 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."

[0091] Conventional systems limited the means by which business entities could efficiently collect information on subsidies and competitor trends and make effective proposals based on that information. Another issue was that the process of analyzing this information and presenting specific profit potential was complex and time-consuming. As a result, it took time and effort for business entities to find the optimal proposal. To solve these problems, a system was needed that integrated and streamlined the processes of collection, analysis, proposal generation, and presentation.

[0092] 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.

[0093] In this invention, the server includes means for inputting the business entity name, business type, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing further detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profit potential, and means for expanding the scope of application using a generative AI model and prompt text. This enables business entities to efficiently collect and analyze the necessary information and easily generate and confirm optimal proposals.

[0094] "Entity name" refers to the official name of a company or organization.

[0095] "Type of business" refers to the type of activity or business conducted by a company or organization.

[0096] "Other necessary information" refers to any additional details required by the system other than the name of the business entity and type of business.

[0097] A "data format" refers to a format for storing and transmitting information digitally. Examples include JSON and XML.

[0098] "Grant Information" refers to information regarding financial assistance provided by government or private sources.

[0099] "Competitor trends" refers to the current activities and market movements of competing companies.

[0100] "Data collection method" refers to the technology or method used by the server to obtain the required information, such as an API call or web scraping.

[0101] "Data analysis tools" refers to techniques and methods for processing collected data and extracting meaningful information. Examples include natural language processing and machine learning.

[0102] "Proposal Ideas" refers to specific plans and strategies for increasing profitability and efficiency of business entities, which are generated based on collected and analyzed data.

[0103] "List display means" refers to a technique or method for visually displaying the generated proposed ideas.

[0104] "Advanced search conditions" refers to search criteria used to narrow down proposed ideas to those that meet specific conditions.

[0105] "Detailed analysis means" refers to techniques and methods for conducting deeper analysis based on detailed search conditions.

[0106] "Specific period" refers to the time or period required to implement the proposed idea.

[0107] "Estimated amount" refers to the budget and expenses required to implement the proposed idea.

[0108] "Profit potential" refers to an indicator that shows how much revenue a proposed idea has the potential to generate.

[0109] "Generative AI model" refers to artificial intelligence techniques or machine learning models used to analyze data and generate meaningful information or recommendations.

[0110] A "prompt sentence" refers to an instruction or inquiry sentence to be input into a generative AI model.

[0111] This invention is a system that efficiently collects and analyzes the information necessary for businesses and organizations (hereinafter referred to as "business entities") to receive support, and generates proposals. This system allows businesses to easily find optimal grant and market opportunities and develop strategies to increase revenue.

[0112] Hardware and software used

[0113] Terminal: A device used by a user to enter the name of the business, type of business, and other necessary information. Examples include a personal computer or smartphone.

[0114] Server: The central processing unit that collects data, analyzes it, and generates recommendations. It can be a cloud-based server or a dedicated server.

[0115] Software: Natural language processing (NLP) libraries (e.g., SpaCy, NLTK), machine learning frameworks (e.g., scikit-learn, TENSORFLOW®), scraping tools for data collection (e.g., BeautifulSoup, Scrapy), libraries for API connectivity (e.g., Requests).

[0116] Program processing flow

[0117] First, the user uses a terminal to input the business entity name (e.g., "Y Corporation"), business type (e.g., "manufacturing"), and other necessary information (e.g., "new product development"). The terminal collects this information and converts it into a standard data format such as JSON. Specifically, it uses JavaScript (registered trademark) or Python functions to convert the data into JSON format.

[0118] The terminal then sends the converted data to the server using an HTTP POST request. The server receives the data and stores it in a database. The server then collects the necessary information from government grant information APIs, news websites, and industry databases. The API requests are sent using Python's Requests library, and the resulting data is received in JSON format. Web scraping can also be performed using BeautifulSoup or Scrapy.

[0119] The collected data is analyzed on a server. At this time, natural language processing technology (SpaCy, NLTK) and machine learning technology (scikit-learn, TensorFlow) are used to generate proposed ideas based on the information entered by the user. For example, if a business is in the manufacturing industry, proposals such as "utilizing digitalization promotion subsidies" or "utilizing new product development support programs" may be generated.

[0120] The server compiles the generated proposal ideas into a list and sends it to the terminal as an HTTP response. The terminal receives this and displays it on the screen in an easy-to-read format for the user. The user selects the proposals that interest them from the list and sets detailed search conditions (e.g., region "Tokyo" and upper budget limit "10 million yen"). The settings are sent back to the server, which performs further detailed analysis.

[0121] The server completes the detailed analysis and generates results including specific timeframes, estimated amounts, and profit potential, which are sent in JSON format to the terminal, which then displays them visually to the user.

[0122] Specific examples

[0123] For example, consider a case where a user is searching for a proposal idea that is likely to generate revenue for a manufacturing business entity, "Y Co., Ltd." The user enters the business entity name, "Y Co., Ltd.", the business type, "manufacturing," and "new product development" into a terminal. The terminal converts this data into JSON format and sends it to the server via an HTTP POST request. The server receives this and collects the latest information from grant information APIs and news websites. The server then uses natural language processing and machine learning techniques to generate proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services for new products."

[0124] The generated proposal ideas are sent in list form to the device, which displays them to the user. When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 10 million yen," the device resends this to the server, which performs a detailed analysis. Finally, the user is provided with information such as the specific project period, required budget, and projected profitability.

[0125] Prompt Sentence Examples

[0126] Enter the following prompt into the generative AI model:

[0127] "The business name is 'Y Co., Ltd.', the business type is 'manufacturing', and the required information is 'new product development'. Please collect the latest subsidy information and competitor trends, and generate proposal ideas that are expected to generate profits based on that information. Display the generated idea list and allow the user to set detailed conditions."

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The user uses the device to enter the business entity name, type of business, and other necessary information. Specifically, the user operates the keyboard or touch panel to enter information such as "Y Co., Ltd.", "manufacturing industry," and "new product development." The entered data is converted to JSON format within the device. For example, the data can be converted to JSON format using the JavaScript JSON.stringify() function.

[0131] Input: Name of business entity, type of business, other necessary information

[0132] Output: Input data in JSON format

[0133] Step 2:

[0134] The terminal sends the converted JSON data to the server. Specifically, the data is sent using an HTTP POST request. The data sent from the terminal is received by the server. The received data is stored in a database.

[0135] Input: Input data in JSON format

[0136] Output: Send data to the server, store data in the database on the server

[0137] Step 3:

[0138] The server uses the collected database to gather information on grants and competitor trends, specifically by using API connections and web scraping. For example, it uses the Requests and BeautifulSoup libraries to gather information from government grant information APIs and industry news sites.

[0139] Input: Data stored in the database on the server

[0140] Output: Subsidy information and competitor trends data

[0141] Step 4:

[0142] The server analyzes the collected data and generates proposal ideas. Specifically, it analyzes the data using natural language processing (NLP) and machine learning models (generative AI models). For example, it uses Scikit-learn and TensorFlow to generate proposals that are beneficial to the business. It creates specific proposal ideas such as "utilizing digitalization promotion subsidies" and "utilizing new product development support programs."

[0143] Input: Grant information and competitor trends data

[0144] Output: Proposed Idea

[0145] Step 5:

[0146] The server compiles the generated proposal ideas into a list and converts it into JSON format. It then sends this to the device using an HTTP response. The device then visually displays the received data to the user using HTML and JavaScript. For example, it displays a list so that the user can easily click to see the details.

[0147] Input: Proposed idea

[0148] Output: A list of proposed ideas sent to the device

[0149] Step 6:

[0150] The user selects ideas that interest them from the suggestions and sets detailed search criteria. For example, they can use drop-down menus and radio buttons to set "Region: Tokyo" and "Budget limit: 10 million yen." The search criteria are then converted back to JSON format and sent to the server using an HTTP POST request.

[0151] Input: Selected proposal idea and detailed search criteria

[0152] Output: Detailed search criteria data in JSON format

[0153] Step 7:

[0154] The server then performs further analysis based on the received search criteria data, such as determining the availability of grants, budget estimates, and profitability forecasts for the selected proposals, by making additional database queries or API requests.

[0155] Input: Detailed search criteria data

[0156] Output: Detailed analysis result data

[0157] Step 8:

[0158] The server converts the detailed analysis results data into JSON format and sends it to the terminal as an HTTP response. The terminal then visually displays the received data to the user using HTML and JavaScript. Specifically, it uses tables and graphs to display detailed results such as specific periods, estimated amounts, and predicted profitability.

[0159] Input: Detailed analysis result data

[0160] Output: Detailed results displayed on the terminal

[0161] (Application example 1)

[0162] 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."

[0163] In conventional logistics centers, data collection on subsidy information and competitor trends is rare, resulting in the problem that formulating an efficient operation strategy takes time and effort. Furthermore, data analysis is insufficient, making it difficult to generate profitable proposal ideas.

[0164] 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.

[0165] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profitability, and means for collecting operational data of the logistics center and proposing strategies for improving efficiency. This makes it possible to formulate an efficient and profitable operational strategy for the logistics center.

[0166] A "business name" is a name used to identify a particular company or organization.

[0167] "Industry" is a category that indicates the classification of a particular industry or business activity.

[0168] A "requirement" is an item of information or data that is essential for the operation of a system or process.

[0169] A "data format" is a format that organizes and structures information in a particular way.

[0170] "Funding Information" means information about funding support or grants provided by governments or other agencies.

[0171] "Competitor activity" is information about the recent activities and strategies of other companies or organizations competing in the same industry.

[0172] "Collection" is the act of gathering necessary data and information.

[0173] "Analysis" is the process of analyzing collected data and information in detail to derive meaning and patterns.

[0174] A "proposal idea" is a concept of a specific plan or strategy for achieving a specific goal.

[0175] "List display" refers to the act of presenting the generated proposed ideas and information to the user in list form.

[0176] "Detailed search conditions" are conditions for obtaining more specific information based on the user's needs.

[0177] "Detailed analysis" is the process of conducting a deeper level of data analysis based on the results of the initial analysis.

[0178] A "period" is a time frame that indicates the duration of a particular activity or project.

[0179] "Estimate" means the projected cost required to carry out a particular project or activity.

[0180] "Profitability" is a measure of how much profit a particular activity or project generates.

[0181] A "logistics center" is a base for storing, distributing, and managing goods.

[0182] "Operational data" refers to information and statistics about the operating status of a particular system or process.

[0183] An efficiency improvement strategy is a plan to improve and optimize the performance of existing processes and systems.

[0184] "Natural language processing" is a technology that allows computers to understand, interpret, and generate human language.

[0185] "Machine learning" is a branch of artificial intelligence in which algorithms improve themselves based on data.

[0186] A "generative AI model" is an artificial intelligence model that can generate new content and predictions based on data.

[0187] A "prompt" is text that is input to a generative AI model and serves to guide the output that the model generates.

[0188] This invention is a system for proposing strategies to improve efficiency in a logistics center. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0189] First, the user uses a terminal to input the company name, industry, and other necessary information. For example, they provide information such as "Company A," "Logistics industry," and "Improvement of transportation efficiency." This information is converted into a data format (e.g., JSON format).

[0190] The converted data is sent from the device to a server, which collects the latest grant information and competitor trends from multiple sources (subsidy information APIs, industry news sites, databases, etc.) using APIs and web scraping technology.

[0191] The collected data is analyzed using natural language processing (NLP) and machine learning (ML) techniques. During the analysis, a generative AI model is used to generate profitable proposal ideas based on user input. For example, it may suggest "optimizing transportation routes" or "introducing a new delivery system."

[0192] The generated proposal ideas are compiled into a list and sent to the device. The user can review this and select the proposal ideas they are interested in. By setting detailed search conditions (e.g., region restrictions, budget limits), the device will again send the conditions to the server.

[0193] The server then performs a more detailed analysis based on the search criteria. Specifically, it calculates the availability of grant funds, budget estimates, and profitability forecasts for the selected proposal ideas. The results of the detailed analysis are sent to the device, where specific information such as the time frame, estimated amount, and profitability are displayed.

[0194] For example, if a user selects "Transportation Route Optimization" for "Company A" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 5 million yen," the server will perform a detailed analysis based on this and provide information such as the specific duration of the initiative, the required budget, and projected profitability.

[0195] An example of a prompt is:

[0196] "A company that operates Logistics Center A is aiming to improve transportation efficiency. Based on information about subsidies and the situation of competitors, please generate profitable proposal ideas and present a specific implementation period and estimated costs."

[0197] This system will enable logistics centers to develop efficient and profitable operational strategies.

[0198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0199] Step 1:

[0200] The user uses the terminal to input the business name, industry, and other necessary information. For example, they provide information such as "Company A," "logistics industry," and "improved transport efficiency." The terminal then converts this information into JSON format. The input includes the data entered by the user, such as "Company A," "logistics industry," and "improved transport efficiency," and the output is the data converted into JSON format.

[0201] Step 2:

[0202] The terminal sends the converted JSON-formatted data to the server. The server saves the received data in preparation for analysis. Specifically, the terminal sends the JSON data as an HTTP POST request, and the server saves the received data in a database. The input is the JSON data sent from the terminal, and the output is in the format saved in the database on the server.

[0203] Step 3:

[0204] The server collects data on grant information and competitor trends from multiple sources (e.g., grant information APIs, industry news sites, and databases). This collection is done using API requests and web scraping techniques. For example, grant information is obtained by sending an API request, and competitor trends are collected by web scraping. The input is the API request or scraping URL from the server, and the output is the obtained grant information and competitor trend data.

[0205] Step 4:

[0206] The server analyzes the collected data using natural language processing (NLP) and machine learning (ML) techniques and generates proposed ideas using a generative AI model. For example, it analyzes grant information and industry news to generate efficiency improvement strategies tailored to the user's needs. The input is the collected grant information and competitor trends data, and the output is a list of generated proposed ideas.

[0207] Step 5:

[0208] The generated proposed ideas are compiled into a list and sent to the device. The device displays the received data on the screen. Specifically, the server sends the proposed idea list to the device in JSON format, which the device parses and displays in a format that is easy for the user to check. The input is the proposed idea list data sent from the server, and the output is the data displayed on the screen.

[0209] Step 6:

[0210] The user selects the proposal ideas that interest them using their device and sets detailed search conditions (e.g., region restriction, budget limit). For example, they enter conditions such as "region: Tokyo" and "budget limit: 5 million yen." The input is the detailed search conditions set by the user, and the output is data converted from those conditions into JSON format.

[0211] Step 7:

[0212] The device sends the set search criteria to the server, which then performs more detailed analysis based on the received criteria. For example, it may determine the availability of subsidies, estimate the budget, or predict profitability. The input is the data for the detailed search criteria sent from the device, and the output is the data of the analysis results.

[0213] Step 8:

[0214] The server generates the results of the detailed analysis and sends them to the terminal. The terminal displays the received data on the screen so that the user can check it. For example, it displays a list of specific time periods, estimated amounts, and profitability information. The input is the data of the detailed analysis results sent from the server, and the output is the specific time period, estimated amounts, and profitability information displayed on the screen.

[0215] 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.

[0216] The present invention provides a system including a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and competitor trends, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability.In addition, by combining this with an emotion engine that recognizes the user's emotions, the system achieves an even more advanced user experience.

[0217] Step 1: User Input and Initial Settings

[0218] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0219] Step 2: Submit your input

[0220] The terminal sends the converted data format information to the server, where a validation check is performed to ensure the data is complete and consistent.

[0221] Step 3: Gathering grant information and competitor trends

[0222] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0223] Step 4: Analyze user emotions with the emotion engine

[0224] The emotion engine analyzes facial expressions and voice data while the user is typing or operating the device, and recognizes the user's emotional state in real time. This emotional data is also sent to the server and used for analysis.

[0225] Step 5: Analyze the data and generate proposal ideas

[0226] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it considers ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0227] Step 6: Listing the proposed ideas

[0228] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0229] Step 7: Setting advanced search criteria

[0230] Users select ideas that interest them and set detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0231] Step 8: Detailed analysis

[0232] The server then performs a more detailed analysis based on the search criteria set by the user, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts.

[0233] Step 9: View detailed results

[0234] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0235] Specific examples

[0236] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. Furthermore, the emotion engine analyzes the user's emotions from their facial expressions and voice while they are entering information, and their emotional state is also sent as data to the server.

[0237] The server analyzes this data and generates proposal ideas such as "Utilizing the Digitalization Promotion Subsidy" and "Deploying a new product as a cloud service." When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets detailed conditions such as "Region: Tokyo" and "Budget Limit: 10 million yen," the server performs a detailed analysis based on this and provides information such as the specific implementation period, required budget, and projected profitability. The user's emotional state is also continuously monitored, allowing for interactive responses tailored to the displayed results.

[0238] The processing flow will be explained below.

[0239] Step 1:

[0240] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0241] Step 2:

[0242] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0243] Step 3:

[0244] The device sends the user's facial expressions and voice to the emotion engine in real time to collect the user's emotional data. The emotion engine analyzes the emotional data and identifies the user's emotional state. This emotional data is also converted into JSON format and sent to the server.

[0245] Step 4:

[0246] The server receives the JSON data (input information and emotion data) sent from the device and prepares it for analysis.

[0247] Step 5:

[0248] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0249] Step 6:

[0250] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it could suggest ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0251] Step 7:

[0252] The server generates a list of proposed ideas and sends it to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0253] Step 8:

[0254] The user selects the ideas they are interested in from the suggestions and sets detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0255] Step 9:

[0256] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0257] Step 10:

[0258] The server receives the detailed search conditions and emotion data and performs further detailed analysis, including determining whether or not to use subsidies based on the newly set conditions, estimating budgets, and forecasting revenue.

[0259] Step 11:

[0260] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0261] Step 12:

[0262] The device analyzes the detailed results received from the server and visually displays them for the user to review. The display includes specific timeframes, estimated amounts, and profitability information. The emotion engine continuously monitors the user's emotions and provides interactive responses tailored to the displayed results.

[0263] Step 13:

[0264] The user reviews the detailed results presented and makes a final decision. The emotion engine analyzes the user's emotional state and provides appropriate advice and guidance when support is required.

[0265] Example 2

[0266] 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."

[0267] In today's business environment, companies need to quickly and accurately grasp a wide range of information, such as subsidy information and competitor trends. They also need to generate specific proposal ideas and create detailed, actionable plans based on this information. However, existing systems often take time to collect and analyze large amounts of data and are unable to provide interactive responses that take into account the user's emotional state. This makes it difficult for companies to receive the appropriate support at the right time.

[0268] 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.

[0269] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for analyzing the user's emotions using an emotion recognition engine and transmitting the emotion data to the server, and means for displaying the specific period, estimated amount, and profitability. This allows users to quickly and accurately obtain proposal ideas, and further enables interactive and individual responses through real-time emotion analysis.

[0270] "Business name" refers to the name of a company or organization.

[0271] "Industry" refers to the type or category of business conducted by a company or organization.

[0272] "Requirements" refers to items of information that a user must enter in order for the system to function properly.

[0273] "Input information" refers to the collection of data that a user provides to a system.

[0274] "Data format" refers to a particular format for structuring information.

[0275] "Subsidy information" refers to information about various subsidies that companies and organizations can apply for.

[0276] "Competitors" refers to other companies or organizations in the same market or industry that offer similar products or services.

[0277] "Trends" refers to current trends and changes in a market or industry.

[0278] "Means of collecting data" refers to the mechanisms and tools used to obtain the necessary information.

[0279] "Means of analysis" refers to the mechanisms and methods for analyzing and processing collected data.

[0280] "Proposed Ideas" refers to specific action plans that are generated based on the collected and analyzed information.

[0281] The "means for displaying a list" refers to a method for visually presenting the generated proposed ideas to the user.

[0282] "Advanced search conditions" refer to conditions set by the user to further narrow down the proposed ideas.

[0283] An "emotion recognition engine" refers to technology for analyzing a user's emotional state in real time.

[0284] The "specific period" refers to the period during which the action to be taken is to be carried out.

[0285] "Estimated Amount" refers to an estimate of the costs required to implement the proposed idea.

[0286] "Profitability" refers to an indicator that evaluates the economic benefits that a proposed idea brings.

[0287] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[0288] "Machine learning" refers to a technology that analyzes data, automatically learns, and makes predictions and judgments.

[0289] A "structured data format" refers to a data format that is organized based on specific rules.

[0290] The present invention provides a system that enables companies and businesses to quickly provide optimal subsidy information and specific proposal ideas, and also enables interactive responses that take into account the emotional state of the user. Specific embodiments of the system are described below.

[0291] First, the user uses the terminal to enter the company name, industry, and other necessary information. For example, if the entered information is "X Corporation," "manufacturing," and "new product development," the terminal collects this information and converts it into a data format such as JSON. The terminal then sends the converted data to the server. At this time, the terminal performs a validation check to ensure the data is complete and consistent.

[0292] Based on the received data, the server collects data on the latest grant information and competitor trends from multiple sources, specifically using API calls and web scraping techniques to obtain information from government grant APIs, industry news sites, etc. The collected data is then stored in an internal database.

[0293] Furthermore, an emotion recognition engine is used to analyze the user's emotions. While the user is typing or operating the device, facial expressions and voice data are captured using a webcam and microphone, and an analysis algorithm is used to recognize the user's emotional state. This emotional data is sent to the server and used for subsequent analysis.

[0294] The server analyzes the collected data and emotional data. Specifically, it applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" are considered.

[0295] The generated proposal ideas are sent from the server to the device, which displays them in list form to the user. The user selects the proposal ideas that interest them from the displayed list and sets detailed search conditions (e.g., "Area limited: Tokyo," "Budget limit: 10 million yen"). The emotion recognition engine analyzes changes in the user's emotions and suggests or adjusts search conditions as necessary.

[0296] The server then performs a more detailed analysis based on the search criteria that was set, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts. The detailed analysis results generated by the server are sent to the terminal, and specific information on the period, estimated amount, and profitability is presented to the user.

[0297] For example, when a user enters "X Corporation," "manufacturing," and "new product development," the device converts this into JSON format, resulting in something like "{ 'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The device then sends this data to the server, which uses government_grants_api and industry_news_scraper to collect information on grants and competitor trends. The acquired data is analyzed, and proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services" are generated.

[0298] (Example of a specific prompt sentence)

[0299] "Please tell me about digitalization subsidies related to new product development in the manufacturing industry. The specific conditions are that they are limited to Tokyo and have a budget cap of 10 million yen."

[0300] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0301] Step 1:

[0302] The user uses the terminal to enter the company name, industry, and other necessary information. For example, they might enter information such as "X Corporation, manufacturing, new product development." The terminal receives this input information and converts it into a data format such as JSON. Specific input data is text information such as "X Corporation" and "manufacturing," which is converted into structured data such as "{'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The converted data is then ready to be sent to the server.

[0303] Step 2:

[0304] The terminal sends the information in the converted data format to the server. At this time, the terminal performs a validation check to maintain the completeness and consistency of the data. Specifically, it checks whether the input data is missing or is in the correct format. For example, it checks whether the company name "X Co., Ltd." is in the correct format and whether the industry is within the options. Once the check is complete, the data is sent to the server via an HTTP request. The server checks the contents of the received data and proceeds with the next process.

[0305] Step 3:

[0306] The server collects data on grant information and competitor trends from multiple sources. Specifically, it calls government grant APIs and web scrapes industry news sites. This process involves sending requests to API endpoints to obtain grant information in JSON format. It also uses web scraping tools to obtain competitor news articles and analytical reports. The collected data is stored in the server's internal database. This allows it to accumulate the latest grant information and competitor trends.

[0307] Step 4:

[0308] An emotion recognition engine analyzes facial and voice data while the user is typing or operating the device to recognize the user's emotional state. For example, a webcam or microphone can be used to capture the user's facial expressions and tone of voice. This data is analyzed in real time to identify the user's emotional state (e.g., joy, surprise, distress, etc.). This emotional data is also sent to the server and used as material for analysis along with other data.

[0309] Step 5:

[0310] The server performs analysis using the collected data and emotional data. It then applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's needs and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" may be generated. The server then compiles these proposal ideas into a list and records the selection process. This allows the server to verify that the generated proposal ideas are based on concrete evidence.

[0311] Step 6:

[0312] The generated proposal ideas are sent to the device. The device receives them and displays them on the screen in list format so that the user can easily check them. For example, each proposal idea can be presented in an easy-to-understand card format, with links and buttons for the user to view the details. This list-format proposal display allows the user to compare and select at a glance.

[0313] Step 7:

[0314] Users select proposal ideas that interest them from a list and set detailed search criteria. For example, they can enter regional restrictions (e.g., "Tokyo") or budget limits (e.g., "10 million yen"). While they are entering their search criteria, the emotion recognition engine analyzes the user's emotional changes and makes appropriate suggestions or adjustments. The input data based on the detailed search criteria is sent to the server, where further detailed analysis begins.

[0315] Step 8:

[0316] The server performs further detailed analysis based on the set search criteria. Based on the newly set criteria, it determines whether grants are available, estimates budgets, and forecasts revenue. It uses data analysis tools to generate detailed reports, such as "subsidies available based on local conditions," recommended "budget plans," and "projected profitability." The analysis results are prepared for the next step.

[0317] Step 9:

[0318] The server generates detailed analysis results and sends them to the terminal, which then displays specific information on the duration, estimated cost, and profitability. The terminal then receives this information and displays it on the screen in a format that is easy for the user to understand. For example, presenting information using visual elements, such as a Gantt chart showing the project duration or a bar chart showing a comparison of costs and profitability, helps users understand the information better.

[0319] In this way, the system can effectively carry out a series of processes from user input to providing detailed analysis results.

[0320] (Application example 2)

[0321] 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."

[0322] This invention aims to improve productivity in factories by analyzing the latest subsidy information and competitor trends to generate and display specific and profitable proposal ideas, thereby solving the problem of realizing an efficient manufacturing process. It is also required to increase user satisfaction and interest by taking into account the user's emotional state.

[0323] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the name of the business, type of business, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposed ideas, means for analyzing the user's emotional state using an emotion recognition engine and transmitting the data, means for displaying a list of the generated proposed ideas, means for setting detailed search conditions for the proposed ideas, means for performing further detailed analysis based on the set search conditions, and means for displaying specific periods, estimated amounts, and profitability. This makes it possible to generate and display profitable proposed ideas that take the user's emotions into consideration.

[0324] "Business name" is the name of a corporation or sole proprietorship.

[0325] "Industry" refers to the type of industry to which a business operator belongs.

[0326] "Required information" refers to information required to identify businesses and generate proposal ideas.

[0327] "Input information" refers to the business name, industry, and other necessary information that the user provides to the system.

[0328] A "data format" is input information converted into a form that is easy for a program to process.

[0329] "Grant Information" refers to detailed data about grants.

[0330] "Competitor Trends" is data that shows the activities and strategies of competitors in the market.

[0331] "Means of collecting data" refers to methods and technologies for obtaining subsidy information and competitor trends.

[0332] "Means for analyzing data" refers to the technology that processes collected data to generate useful proposal ideas.

[0333] "Proposed ideas" are specific initiatives that will increase profitability and efficiency for users.

[0334] An "emotion recognition engine" is a technology that analyzes a user's emotional state from their facial expressions and voice.

[0335] "Emotion data" is information about the user's emotional state obtained by an emotion recognition engine.

[0336] The "means for displaying proposed ideas" is a technique for visually presenting the generated proposed ideas in a format that can be confirmed by the user.

[0337] The "detailed search conditions" indicate the user's specific requirements and constraints for the proposed idea.

[0338] The "means for performing detailed analysis based on search conditions" is a technique for performing more specific data analysis based on detailed search conditions set by the user.

[0339] The "specific period" refers to the time required to implement the proposed idea.

[0340] The "estimated amount" is the budget amount required to implement the proposed idea.

[0341] "Profitability" refers to the revenue expected from implementing the proposed idea.

[0342] In this invention, the system operates in the following steps.

[0343] First, the user uses a tablet device to enter the business name, industry, and other necessary information. Specifically, they enter the company name, industry type (e.g., manufacturing), and specific project name (e.g., new product development). This information is converted into a data format and sent to the server in a standard format such as JSON. This ensures data consistency and integrity.

[0344] The server then uses multiple sources to gather data on grant information and competitor activity, including government APIs, industry news sites, and other trusted databases to obtain the latest information, using techniques such as API calls and web scraping.

[0345] The emotion recognition engine then analyzes the user's emotional state. The engine analyzes the user's facial expressions and voice data as they are inputting, recognizing their emotional state in real time. This emotional data is also sent to the server and used for analysis in the next step.

[0346] The collected data and sentiment data are analyzed using natural language processing (NLP) and machine learning (ML) algorithms. This generates profitable proposal ideas. For example, specific proposals such as utilizing digitalization promotion subsidies or developing cloud services for new products are considered. The generated proposal ideas are compiled into a list and sent to the device, where they are displayed to the user.

[0347] Users can set detailed search conditions for proposed ideas, such as region restrictions or budget limits. Based on the set search conditions, the server performs further detailed analysis. The detailed analysis includes determining whether or not subsidies can be used based on the newly set conditions, budget estimates, revenue forecasts, etc.

[0348] Finally, the server sends the results of the detailed analysis to the terminal, and the specific time frame, estimated cost, and profitability information are displayed to the user, providing them with specific and actionable suggestions for improving profitability and efficiency.

[0349] Hardware and Software Used

[0350] The hardware used mainly includes tablets and factory robots, while the software uses an emotion recognition engine (EmotionEngine), natural language processing and machine learning libraries (NLP and ML), and a REST API.

[0351] Specific examples

[0352] For example, a factory worker is searching for information on subsidies for a new product. When the worker uses a tablet to enter the necessary information, an emotion recognition engine analyzes the worker's emotional state, such as interest and stress level, from his facial expressions and voice. The server analyzes the collected subsidy information and competitive information and generates specific proposals such as "utilizing digitalization promotion subsidies." When the worker sets more detailed conditions for this proposal, the server performs detailed analysis, such as budget estimates and revenue forecasts, and displays the results.

[0353] Prompt Sentence Examples

[0354] You are an assistant tasked with generating proposal ideas that will contribute to improving factory productivity based on the information below. Please come up with ideas based on the information below.

[0355] Factory Information:

[0356] Business name: Y Co., Ltd.

[0357] Industry: Manufacturing

[0358] Process: New Product Development

[0359] Grant information: [JSON data of grant information]

[0360] Competitor Information: [JSON data of competitor information]

[0361] Worker emotional state: [JSON data of emotion data]

[0362] request:

[0363] Generate three proposal ideas.

[0364] For each proposal, explain the projected profitability.

[0365] View the list of suggestions.

[0366] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0367] Step 1:

[0368] The user uses a tablet device to enter the business name, industry, and other necessary information. This allows for the collection of corporate names, industry types, and specific project names such as new product development. The entered information is converted into a data format such as JSON and sent to the server. Input is done in text or multiple choice format, and the information converted into data format is output.

[0369] Step 2:

[0370] The server receives the submitted data and validates it for consistency and completeness. Data that passes the validation checks is used to collect data on grant information and competitor trends. The input is transformed JSON data and the output is a valid dataset.

[0371] Step 3:

[0372] The server uses government APIs, industry news sites, and other reliable databases to collect the latest grant information. It also collects competitors' technology and productivity improvement trends. This information is collected using API calls and web scraping. The input is the API key and web scraping settings, and the output is the latest grant information and competitor trends.

[0373] Step 4:

[0374] While the user is inputting, the emotion recognition engine analyzes the user's facial expression and voice data to recognize their emotional state in real time. This emotion data is also sent to the server and used for analysis in the next step. The input is the user's facial expression and voice data, and the output is the analyzed emotion data.

[0375] Step 5:

[0376] The server analyzes the collected grant information, competitive information, and user sentiment data. It uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas. Specific proposal ideas considered include "utilizing digitalization promotion subsidies" and "developing cloud services for new products." The input is the collected dataset and sentiment data, and the output is the generated proposal ideas.

[0377] Step 6:

[0378] The generated proposal ideas are compiled in list form and sent to the terminal. The user can check this and view the details of each proposal idea. The input is the generated proposal ideas, and the output is the proposal ideas compiled in list form.

[0379] Step 7:

[0380] Users input detailed search criteria for their proposed ideas, such as geographical restrictions or budget limits. The system uses an emotion recognition engine to suggest and adjust search criteria as needed. The input is the detailed search criteria set by the user, and the output is a dataset that reflects the detailed search criteria.

[0381] Step 8:

[0382] The server performs further detailed analysis based on the set detailed search conditions. Based on the newly set conditions, it determines whether or not subsidies can be used, estimates budgets, and predicts revenue. The input is the detailed search conditions, and the output is the results of the detailed analysis.

[0383] Step 9:

[0384] The server generates the results of the detailed analysis and sends them to the terminal. The user can then check the specific period, estimated amount, and profitability information. The input is the detailed analysis results, and the output is the specific period, estimated amount, and profitability information.

[0385] Through these processing steps, users can obtain specific and actionable suggestions for increasing profitability and efficiency.

[0386] 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.

[0387] 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.

[0388] 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.

[0389] [Second embodiment]

[0390] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0401] 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."

[0402] The present invention is a system that includes a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and the trends of competitors, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability. A specific method for implementing this system is described below.

[0403] Step 1: User Input and Initial Settings

[0404] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0405] Step 2: Submit your input

[0406] The device sends the converted data format information to the server, which then prepares the data for analysis.

[0407] Step 3: Gathering grant information and competitor trends

[0408] The server collects data on the latest grant information and competitor trends from multiple sources (government grant information API, industry news sites, databases, etc.) The server efficiently obtains the required information using APIs and web scraping technology.

[0409] Step 4: Analyze the data and generate proposal ideas

[0410] The server analyzes the collected data and uses natural language processing and machine learning technologies to generate profitable proposal ideas based on the user's input, such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products."

[0411] Step 5: Listing the proposed ideas

[0412] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0413] Step 6: Setting advanced search criteria

[0414] The user selects ideas that interest them from the suggestions and sets detailed search conditions (e.g., region restrictions, budget limits, etc.). The device then sends these conditions back to the server.

[0415] Step 7: Detailed analysis

[0416] The server then performs further analysis based on the search criteria set by the user, specifically providing grant availability, budget estimates, and profitability forecasts for the selected proposal ideas.

[0417] Step 8: View detailed results

[0418] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0419] Specific examples

[0420] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. The server then analyzes this data and generates proposal ideas such as "utilizing the digitalization promotion subsidy" and "developing a cloud service for a new product." When the user selects "utilizing the digitalization promotion subsidy" and sets the detailed conditions, such as "region: Tokyo" and "maximum budget: 10 million yen," the server performs a detailed analysis based on this information and can provide information such as the specific implementation period, required budget, and projected profitability.

[0421] The processing flow will be explained below.

[0422] Step 1:

[0423] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0424] Step 2:

[0425] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0426] Step 3:

[0427] The server receives the JSON data sent from the device and prepares it for analysis.

[0428] Step 4:

[0429] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0430] Step 5:

[0431] The server analyzes the collected data and uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input.

[0432] Step 6:

[0433] The server compiles the generated proposal ideas into a list, including ideas such as "utilizing digitalization promotion subsidies" and "developing new product cloud services."

[0434] Step 7:

[0435] The server sends the list of proposed ideas to the terminal in JSON format, ensuring data integrity and security.

[0436] Step 8:

[0437] The terminal analyzes the list of proposed ideas received from the server and visually displays them, from which the user can select the proposed ideas that interest them.

[0438] Step 9:

[0439] Users can select specific proposal ideas and set detailed search conditions, such as "Region: Tokyo" or "Budget limit: 10 million yen."

[0440] Step 10:

[0441] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0442] Step 11:

[0443] The server receives the detailed search conditions and performs further detailed analysis, including determining whether or not grants can be used based on the newly set conditions, budget estimates, and revenue forecasts.

[0444] Step 12:

[0445] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0446] Step 13:

[0447] The terminal analyzes the detailed results received from the server and visually displays them for the user to review, including specific timeframes, estimated costs, and profitability information.

[0448] In this way, users can efficiently and effectively obtain proposal ideas that are likely to generate profits.

[0449] Example 1

[0450] 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."

[0451] Conventional systems limited the means by which business entities could efficiently collect information on subsidies and competitor trends and make effective proposals based on that information. Another issue was that the process of analyzing this information and presenting specific profit potential was complex and time-consuming. As a result, it took time and effort for business entities to find the optimal proposal. To solve these problems, a system was needed that integrated and streamlined the processes of collection, analysis, proposal generation, and presentation.

[0452] 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.

[0453] In this invention, the server includes means for inputting the business entity name, business type, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing further detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profit potential, and means for expanding the scope of application using a generative AI model and prompt text. This enables business entities to efficiently collect and analyze the necessary information and easily generate and confirm optimal proposals.

[0454] "Entity name" refers to the official name of a company or organization.

[0455] "Type of business" refers to the type of activity or business conducted by a company or organization.

[0456] "Other necessary information" refers to any additional details required by the system other than the name of the business entity and type of business.

[0457] A "data format" refers to a format for storing and transmitting information digitally. Examples include JSON and XML.

[0458] "Grant Information" refers to information regarding financial assistance provided by government or private sources.

[0459] "Competitor trends" refers to the current activities and market movements of competing companies.

[0460] "Data collection method" refers to the technology or method used by the server to obtain the required information, such as an API call or web scraping.

[0461] "Data analysis tools" refers to techniques and methods for processing collected data and extracting meaningful information. Examples include natural language processing and machine learning.

[0462] "Proposal Ideas" refers to specific plans and strategies for increasing profitability and efficiency of business entities, which are generated based on collected and analyzed data.

[0463] "List display means" refers to a technique or method for visually displaying the generated proposed ideas.

[0464] "Advanced search conditions" refers to search criteria used to narrow down proposed ideas to those that meet specific conditions.

[0465] "Detailed analysis means" refers to techniques and methods for conducting deeper analysis based on detailed search conditions.

[0466] "Specific period" refers to the time or period required to implement the proposed idea.

[0467] "Estimated amount" refers to the budget and expenses required to implement the proposed idea.

[0468] "Profit potential" refers to an indicator that shows how much revenue a proposed idea has the potential to generate.

[0469] "Generative AI model" refers to artificial intelligence techniques or machine learning models used to analyze data and generate meaningful information or recommendations.

[0470] A "prompt sentence" refers to an instruction or inquiry sentence to be input into a generative AI model.

[0471] This invention is a system that efficiently collects and analyzes the information necessary for businesses and organizations (hereinafter referred to as "business entities") to receive support, and generates proposals. This system allows businesses to easily find optimal grant and market opportunities and develop strategies to increase revenue.

[0472] Hardware and software used

[0473] Terminal: A device used by a user to enter the name of the business, type of business, and other necessary information. Examples include a personal computer or smartphone.

[0474] Server: The central processing unit that collects data, analyzes it, and generates recommendations. It can be a cloud-based server or a dedicated server.

[0475] Software: Natural language processing (NLP) libraries (e.g., SpaCy, NLTK), machine learning frameworks (e.g., scikit-learn, TensorFlow), scraping tools for data collection (e.g., BeautifulSoup, Scrapy), libraries for API connectivity (e.g., Requests).

[0476] Program processing flow

[0477] First, the user uses a terminal to input the business entity name (e.g., "Y Corporation"), business type (e.g., "manufacturing"), and other necessary information (e.g., "new product development"). The terminal collects this information and converts it into a standard data format such as JSON. Specifically, it uses JavaScript or Python functions to convert the data into JSON format.

[0478] The terminal then sends the converted data to the server using an HTTP POST request. The server receives the data and stores it in a database. The server then collects the necessary information from government grant information APIs, news websites, and industry databases. The API requests are sent using Python's Requests library, and the resulting data is received in JSON format. Web scraping can also be performed using BeautifulSoup or Scrapy.

[0479] The collected data is analyzed on a server. At this time, natural language processing technology (SpaCy, NLTK) and machine learning technology (scikit-learn, TensorFlow) are used to generate proposed ideas based on the information entered by the user. For example, if a business is in the manufacturing industry, proposals such as "utilizing digitalization promotion subsidies" or "utilizing new product development support programs" may be generated.

[0480] The server compiles the generated proposal ideas into a list and sends it to the terminal as an HTTP response. The terminal receives this and displays it on the screen in an easy-to-read format for the user. The user selects the proposals that interest them from the list and sets detailed search conditions (e.g., region "Tokyo" and upper budget limit "10 million yen"). The settings are sent back to the server, which performs further detailed analysis.

[0481] The server completes the detailed analysis and generates results including specific timeframes, estimated amounts, and profit potential, which are sent in JSON format to the terminal, which then displays them visually to the user.

[0482] Specific examples

[0483] For example, consider a case where a user is searching for a proposal idea that is likely to generate revenue for a manufacturing business entity, "Y Co., Ltd." The user enters the business entity name, "Y Co., Ltd.", the business type, "manufacturing," and "new product development" into a terminal. The terminal converts this data into JSON format and sends it to the server via an HTTP POST request. The server receives this and collects the latest information from grant information APIs and news websites. The server then uses natural language processing and machine learning techniques to generate proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services for new products."

[0484] The generated proposal ideas are sent in list form to the device, which displays them to the user. When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 10 million yen," the device resends this to the server, which performs a detailed analysis. Finally, the user is provided with information such as the specific project period, required budget, and projected profitability.

[0485] Prompt Sentence Examples

[0486] Enter the following prompt into the generative AI model:

[0487] "The business name is 'Y Co., Ltd.', the business type is 'manufacturing', and the required information is 'new product development'. Please collect the latest subsidy information and competitor trends, and generate proposal ideas that are expected to generate profits based on that information. Display the generated idea list and allow the user to set detailed conditions."

[0488] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0489] Step 1:

[0490] The user uses the device to enter the business entity name, type of business, and other necessary information. Specifically, the user operates the keyboard or touch panel to enter information such as "Y Co., Ltd.", "manufacturing industry," and "new product development." The entered data is converted to JSON format within the device. For example, the data can be converted to JSON format using the JavaScript JSON.stringify() function.

[0491] Input: Name of business entity, type of business, other necessary information

[0492] Output: Input data in JSON format

[0493] Step 2:

[0494] The terminal sends the converted JSON data to the server. Specifically, the data is sent using an HTTP POST request. The data sent from the terminal is received by the server. The received data is stored in a database.

[0495] Input: Input data in JSON format

[0496] Output: Send data to the server, store data in the database on the server

[0497] Step 3:

[0498] The server uses the collected database to gather information on grants and competitor trends, specifically by using API connections and web scraping. For example, it uses the Requests and BeautifulSoup libraries to gather information from government grant information APIs and industry news sites.

[0499] Input: Data stored in the database on the server

[0500] Output: Subsidy information and competitor trends data

[0501] Step 4:

[0502] The server analyzes the collected data and generates proposal ideas. Specifically, it analyzes the data using natural language processing (NLP) and machine learning models (generative AI models). For example, it uses Scikit-learn and TensorFlow to generate proposals that are beneficial to the business. It creates specific proposal ideas such as "utilizing digitalization promotion subsidies" and "utilizing new product development support programs."

[0503] Input: Grant information and competitor trends data

[0504] Output: Proposed Idea

[0505] Step 5:

[0506] The server compiles the generated proposal ideas into a list and converts it into JSON format. It then sends this to the device using an HTTP response. The device then visually displays the received data to the user using HTML and JavaScript. For example, it displays a list so that the user can easily click to see the details.

[0507] Input: Proposed idea

[0508] Output: A list of proposed ideas sent to the device

[0509] Step 6:

[0510] The user selects ideas that interest them from the suggestions and sets detailed search criteria. For example, they can use drop-down menus and radio buttons to set "Region: Tokyo" and "Budget limit: 10 million yen." The search criteria are then converted back to JSON format and sent to the server using an HTTP POST request.

[0511] Input: Selected proposal idea and detailed search criteria

[0512] Output: Detailed search criteria data in JSON format

[0513] Step 7:

[0514] The server then performs further analysis based on the received search criteria data, such as determining the availability of grants, budget estimates, and profitability forecasts for the selected proposals, by making additional database queries or API requests.

[0515] Input: Detailed search criteria data

[0516] Output: Detailed analysis result data

[0517] Step 8:

[0518] The server converts the detailed analysis results data into JSON format and sends it to the terminal as an HTTP response. The terminal then visually displays the received data to the user using HTML and JavaScript. Specifically, it uses tables and graphs to display detailed results such as specific periods, estimated amounts, and predicted profitability.

[0519] Input: Detailed analysis result data

[0520] Output: Detailed results displayed on the terminal

[0521] (Application example 1)

[0522] 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."

[0523] In conventional logistics centers, data collection on subsidy information and competitor trends is rare, resulting in the problem that formulating an efficient operation strategy takes time and effort. Furthermore, data analysis is insufficient, making it difficult to generate profitable proposal ideas.

[0524] 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.

[0525] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profitability, and means for collecting operational data of the logistics center and proposing strategies for improving efficiency. This makes it possible to formulate an efficient and profitable operational strategy for the logistics center.

[0526] A "business name" is a name used to identify a particular company or organization.

[0527] "Industry" is a category that indicates the classification of a particular industry or business activity.

[0528] A "requirement" is an item of information or data that is essential for the operation of a system or process.

[0529] A "data format" is a format that organizes and structures information in a particular way.

[0530] "Funding Information" means information about funding support or grants provided by governments or other agencies.

[0531] "Competitor activity" is information about the recent activities and strategies of other companies or organizations competing in the same industry.

[0532] "Collection" is the act of gathering necessary data and information.

[0533] "Analysis" is the process of analyzing collected data and information in detail to derive meaning and patterns.

[0534] A "proposal idea" is a concept of a specific plan or strategy for achieving a specific goal.

[0535] "List display" refers to the act of presenting the generated proposed ideas and information to the user in list form.

[0536] "Detailed search conditions" are conditions for obtaining more specific information based on the user's needs.

[0537] "Detailed analysis" is the process of conducting a deeper level of data analysis based on the results of the initial analysis.

[0538] A "period" is a time frame that indicates the duration of a particular activity or project.

[0539] "Estimate" means the projected cost required to carry out a particular project or activity.

[0540] "Profitability" is a measure of how much profit a particular activity or project generates.

[0541] A "logistics center" is a base for storing, distributing, and managing goods.

[0542] "Operational data" refers to information and statistics about the operating status of a particular system or process.

[0543] An efficiency improvement strategy is a plan to improve and optimize the performance of existing processes and systems.

[0544] "Natural language processing" is a technology that allows computers to understand, interpret, and generate human language.

[0545] "Machine learning" is a branch of artificial intelligence in which algorithms improve themselves based on data.

[0546] A "generative AI model" is an artificial intelligence model that can generate new content and predictions based on data.

[0547] A "prompt" is text that is input to a generative AI model and serves to guide the output that the model generates.

[0548] This invention is a system for proposing strategies to improve efficiency in a logistics center. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0549] First, the user uses a terminal to input the company name, industry, and other necessary information. For example, they provide information such as "Company A," "Logistics industry," and "Improvement of transportation efficiency." This information is converted into a data format (e.g., JSON format).

[0550] The converted data is sent from the device to a server, which collects the latest grant information and competitor trends from multiple sources (subsidy information APIs, industry news sites, databases, etc.) using APIs and web scraping technology.

[0551] The collected data is analyzed using natural language processing (NLP) and machine learning (ML) techniques. During the analysis, a generative AI model is used to generate profitable proposal ideas based on user input. For example, it may suggest "optimizing transportation routes" or "introducing a new delivery system."

[0552] The generated proposal ideas are compiled into a list and sent to the device. The user can review this and select the proposal ideas they are interested in. By setting detailed search conditions (e.g., region restrictions, budget limits), the device will again send the conditions to the server.

[0553] The server then performs a more detailed analysis based on the search criteria. Specifically, it calculates the availability of grant funds, budget estimates, and profitability forecasts for the selected proposal ideas. The results of the detailed analysis are sent to the device, where specific information such as the time frame, estimated amount, and profitability are displayed.

[0554] For example, if a user selects "Transportation Route Optimization" for "Company A" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 5 million yen," the server will perform a detailed analysis based on this and provide information such as the specific duration of the initiative, the required budget, and projected profitability.

[0555] An example of a prompt is:

[0556] "A company that operates Logistics Center A is aiming to improve transportation efficiency. Based on information about subsidies and the situation of competitors, please generate profitable proposal ideas and present a specific implementation period and estimated costs."

[0557] This system will enable logistics centers to develop efficient and profitable operational strategies.

[0558] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0559] Step 1:

[0560] The user uses the terminal to input the business name, industry, and other necessary information. For example, they provide information such as "Company A," "logistics industry," and "improved transport efficiency." The terminal then converts this information into JSON format. The input includes the data entered by the user, such as "Company A," "logistics industry," and "improved transport efficiency," and the output is the data converted into JSON format.

[0561] Step 2:

[0562] The terminal sends the converted JSON-formatted data to the server. The server saves the received data in preparation for analysis. Specifically, the terminal sends the JSON data as an HTTP POST request, and the server saves the received data in a database. The input is the JSON data sent from the terminal, and the output is in the format saved in the database on the server.

[0563] Step 3:

[0564] The server collects data on grant information and competitor trends from multiple sources (e.g., grant information APIs, industry news sites, and databases). This collection is done using API requests and web scraping techniques. For example, grant information is obtained by sending an API request, and competitor trends are collected by web scraping. The input is the API request or scraping URL from the server, and the output is the obtained grant information and competitor trend data.

[0565] Step 4:

[0566] The server analyzes the collected data using natural language processing (NLP) and machine learning (ML) techniques and generates proposed ideas using a generative AI model. For example, it analyzes grant information and industry news to generate efficiency improvement strategies tailored to the user's needs. The input is the collected grant information and competitor trends data, and the output is a list of generated proposed ideas.

[0567] Step 5:

[0568] The generated proposed ideas are compiled into a list and sent to the device. The device displays the received data on the screen. Specifically, the server sends the proposed idea list to the device in JSON format, which the device parses and displays in a format that is easy for the user to check. The input is the proposed idea list data sent from the server, and the output is the data displayed on the screen.

[0569] Step 6:

[0570] The user selects the proposal ideas that interest them using their device and sets detailed search conditions (e.g., region restriction, budget limit). For example, they enter conditions such as "region: Tokyo" and "budget limit: 5 million yen." The input is the detailed search conditions set by the user, and the output is data converted from those conditions into JSON format.

[0571] Step 7:

[0572] The device sends the set search criteria to the server, which then performs more detailed analysis based on the received criteria. For example, it may determine the availability of subsidies, estimate the budget, or predict profitability. The input is the data for the detailed search criteria sent from the device, and the output is the data of the analysis results.

[0573] Step 8:

[0574] The server generates the results of the detailed analysis and sends them to the terminal. The terminal displays the received data on the screen so that the user can check it. For example, it displays a list of specific time periods, estimated amounts, and profitability information. The input is the data of the detailed analysis results sent from the server, and the output is the specific time period, estimated amounts, and profitability information displayed on the screen.

[0575] 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.

[0576] The present invention provides a system including a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and competitor trends, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability.In addition, by combining this with an emotion engine that recognizes the user's emotions, the system achieves an even more advanced user experience.

[0577] Step 1: User Input and Initial Settings

[0578] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0579] Step 2: Submit your input

[0580] The terminal sends the converted data format information to the server, where a validation check is performed to ensure the data is complete and consistent.

[0581] Step 3: Gathering grant information and competitor trends

[0582] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0583] Step 4: Analyze user emotions with the emotion engine

[0584] The emotion engine analyzes facial expressions and voice data while the user is typing or operating the device, and recognizes the user's emotional state in real time. This emotional data is also sent to the server and used for analysis.

[0585] Step 5: Analyze the data and generate proposal ideas

[0586] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it considers ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0587] Step 6: Listing the proposed ideas

[0588] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0589] Step 7: Setting advanced search criteria

[0590] Users select ideas that interest them and set detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0591] Step 8: Detailed analysis

[0592] The server then performs a more detailed analysis based on the search criteria set by the user, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts.

[0593] Step 9: View detailed results

[0594] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0595] Specific examples

[0596] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. Furthermore, the emotion engine analyzes the user's emotions from their facial expressions and voice while they are entering information, and their emotional state is also sent as data to the server.

[0597] The server analyzes this data and generates proposal ideas such as "Utilizing the Digitalization Promotion Subsidy" and "Deploying a new product as a cloud service." When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets detailed conditions such as "Region: Tokyo" and "Budget Limit: 10 million yen," the server performs a detailed analysis based on this and provides information such as the specific implementation period, required budget, and projected profitability. The user's emotional state is also continuously monitored, allowing for interactive responses tailored to the displayed results.

[0598] The processing flow will be explained below.

[0599] Step 1:

[0600] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0601] Step 2:

[0602] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0603] Step 3:

[0604] The device sends the user's facial expressions and voice to the emotion engine in real time to collect the user's emotional data. The emotion engine analyzes the emotional data and identifies the user's emotional state. This emotional data is also converted into JSON format and sent to the server.

[0605] Step 4:

[0606] The server receives the JSON data (input information and emotion data) sent from the device and prepares it for analysis.

[0607] Step 5:

[0608] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0609] Step 6:

[0610] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it could suggest ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0611] Step 7:

[0612] The server generates a list of proposed ideas and sends it to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0613] Step 8:

[0614] The user selects the ideas they are interested in from the suggestions and sets detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0615] Step 9:

[0616] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0617] Step 10:

[0618] The server receives the detailed search conditions and emotion data and performs further detailed analysis, including determining whether or not to use subsidies based on the newly set conditions, estimating budgets, and forecasting revenue.

[0619] Step 11:

[0620] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0621] Step 12:

[0622] The device analyzes the detailed results received from the server and visually displays them for the user to review. The display includes specific timeframes, estimated amounts, and profitability information. The emotion engine continuously monitors the user's emotions and provides interactive responses tailored to the displayed results.

[0623] Step 13:

[0624] The user reviews the detailed results presented and makes a final decision. The emotion engine analyzes the user's emotional state and provides appropriate advice and guidance when support is required.

[0625] Example 2

[0626] 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."

[0627] In today's business environment, companies need to quickly and accurately grasp a wide range of information, such as subsidy information and competitor trends. They also need to generate specific proposal ideas and create detailed, actionable plans based on this information. However, existing systems often take time to collect and analyze large amounts of data and are unable to provide interactive responses that take into account the user's emotional state. This makes it difficult for companies to receive the appropriate support at the right time.

[0628] 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.

[0629] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for analyzing the user's emotions using an emotion recognition engine and transmitting the emotion data to the server, and means for displaying the specific period, estimated amount, and profitability. This allows users to quickly and accurately obtain proposal ideas, and further enables interactive and individual responses through real-time emotion analysis.

[0630] "Business name" refers to the name of a company or organization.

[0631] "Industry" refers to the type or category of business conducted by a company or organization.

[0632] "Requirements" refers to items of information that a user must enter in order for the system to function properly.

[0633] "Input information" refers to the collection of data that a user provides to a system.

[0634] "Data format" refers to a particular format for structuring information.

[0635] "Subsidy information" refers to information about various subsidies that companies and organizations can apply for.

[0636] "Competitors" refers to other companies or organizations in the same market or industry that offer similar products or services.

[0637] "Trends" refers to current trends and changes in a market or industry.

[0638] "Means of collecting data" refers to the mechanisms and tools used to obtain the necessary information.

[0639] "Means of analysis" refers to the mechanisms and methods for analyzing and processing collected data.

[0640] "Proposed Ideas" refers to specific action plans that are generated based on the collected and analyzed information.

[0641] The "means for displaying a list" refers to a method for visually presenting the generated proposed ideas to the user.

[0642] "Advanced search conditions" refer to conditions set by the user to further narrow down the proposed ideas.

[0643] An "emotion recognition engine" refers to technology for analyzing a user's emotional state in real time.

[0644] The "specific period" refers to the period during which the action to be taken is to be carried out.

[0645] "Estimated Amount" refers to an estimate of the costs required to implement the proposed idea.

[0646] "Profitability" refers to an indicator that evaluates the economic benefits that a proposed idea brings.

[0647] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[0648] "Machine learning" refers to a technology that analyzes data, automatically learns, and makes predictions and judgments.

[0649] A "structured data format" refers to a data format that is organized based on specific rules.

[0650] The present invention provides a system that enables companies and businesses to quickly provide optimal subsidy information and specific proposal ideas, and also enables interactive responses that take into account the emotional state of the user. Specific embodiments of the system are described below.

[0651] First, the user uses the terminal to enter the company name, industry, and other necessary information. For example, if the entered information is "X Corporation," "manufacturing," and "new product development," the terminal collects this information and converts it into a data format such as JSON. The terminal then sends the converted data to the server. At this time, the terminal performs a validation check to ensure the data is complete and consistent.

[0652] Based on the received data, the server collects data on the latest grant information and competitor trends from multiple sources, specifically using API calls and web scraping techniques to obtain information from government grant APIs, industry news sites, etc. The collected data is then stored in an internal database.

[0653] Furthermore, an emotion recognition engine is used to analyze the user's emotions. While the user is typing or operating the device, facial expressions and voice data are captured using a webcam and microphone, and an analysis algorithm is used to recognize the user's emotional state. This emotional data is sent to the server and used for subsequent analysis.

[0654] The server analyzes the collected data and emotional data. Specifically, it applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" are considered.

[0655] The generated proposal ideas are sent from the server to the device, which displays them in list form to the user. The user selects the proposal ideas that interest them from the displayed list and sets detailed search conditions (e.g., "Area limited: Tokyo," "Budget limit: 10 million yen"). The emotion recognition engine analyzes changes in the user's emotions and suggests or adjusts search conditions as necessary.

[0656] The server then performs a more detailed analysis based on the search criteria that was set, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts. The detailed analysis results generated by the server are sent to the terminal, and specific information on the period, estimated amount, and profitability is presented to the user.

[0657] For example, when a user enters "X Corporation," "manufacturing," and "new product development," the device converts this into JSON format, resulting in something like "{ 'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The device then sends this data to the server, which uses government_grants_api and industry_news_scraper to collect information on grants and competitor trends. The acquired data is analyzed, and proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services" are generated.

[0658] (Example of a specific prompt sentence)

[0659] "Please tell me about digitalization subsidies related to new product development in the manufacturing industry. The specific conditions are that they are limited to Tokyo and have a budget cap of 10 million yen."

[0660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0661] Step 1:

[0662] The user uses the terminal to enter the company name, industry, and other necessary information. For example, they might enter information such as "X Corporation, manufacturing, new product development." The terminal receives this input information and converts it into a data format such as JSON. Specific input data is text information such as "X Corporation" and "manufacturing," which is converted into structured data such as "{'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The converted data is then ready to be sent to the server.

[0663] Step 2:

[0664] The terminal sends the information in the converted data format to the server. At this time, the terminal performs a validation check to maintain the completeness and consistency of the data. Specifically, it checks whether the input data is missing or is in the correct format. For example, it checks whether the company name "X Co., Ltd." is in the correct format and whether the industry is within the options. Once the check is complete, the data is sent to the server via an HTTP request. The server checks the contents of the received data and proceeds with the next process.

[0665] Step 3:

[0666] The server collects data on grant information and competitor trends from multiple sources. Specifically, it calls government grant APIs and web scrapes industry news sites. This process involves sending requests to API endpoints to obtain grant information in JSON format. It also uses web scraping tools to obtain competitor news articles and analytical reports. The collected data is stored in the server's internal database. This allows it to accumulate the latest grant information and competitor trends.

[0667] Step 4:

[0668] An emotion recognition engine analyzes facial and voice data while the user is typing or operating the device to recognize the user's emotional state. For example, a webcam or microphone can be used to capture the user's facial expressions and tone of voice. This data is analyzed in real time to identify the user's emotional state (e.g., joy, surprise, distress, etc.). This emotional data is also sent to the server and used as material for analysis along with other data.

[0669] Step 5:

[0670] The server performs analysis using the collected data and emotional data. It then applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's needs and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" may be generated. The server then compiles these proposal ideas into a list and records the selection process. This allows the server to verify that the generated proposal ideas are based on concrete evidence.

[0671] Step 6:

[0672] The generated proposal ideas are sent to the device. The device receives them and displays them on the screen in list format so that the user can easily check them. For example, each proposal idea can be presented in an easy-to-understand card format, with links and buttons for the user to view the details. This list-format proposal display allows the user to compare and select at a glance.

[0673] Step 7:

[0674] Users select proposal ideas that interest them from a list and set detailed search criteria. For example, they can enter regional restrictions (e.g., "Tokyo") or budget limits (e.g., "10 million yen"). While they are entering their search criteria, the emotion recognition engine analyzes the user's emotional changes and makes appropriate suggestions or adjustments. The input data based on the detailed search criteria is sent to the server, where further detailed analysis begins.

[0675] Step 8:

[0676] The server performs further detailed analysis based on the set search criteria. Based on the newly set criteria, it determines whether grants are available, estimates budgets, and forecasts revenue. It uses data analysis tools to generate detailed reports, such as "subsidies available based on local conditions," recommended "budget plans," and "projected profitability." The analysis results are prepared for the next step.

[0677] Step 9:

[0678] The server generates detailed analysis results and sends them to the terminal, which then displays specific information on the duration, estimated cost, and profitability. The terminal then receives this information and displays it on the screen in a format that is easy for the user to understand. For example, presenting information using visual elements, such as a Gantt chart showing the project duration or a bar chart showing a comparison of costs and profitability, helps users understand the information better.

[0679] In this way, the system can effectively carry out a series of processes from user input to providing detailed analysis results.

[0680] (Application example 2)

[0681] 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."

[0682] This invention aims to improve productivity in factories by analyzing the latest subsidy information and competitor trends to generate and display specific and profitable proposal ideas, thereby solving the problem of realizing an efficient manufacturing process. It is also required to increase user satisfaction and interest by taking into account the user's emotional state.

[0683] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the name of the business, type of business, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposed ideas, means for analyzing the user's emotional state using an emotion recognition engine and transmitting the data, means for displaying a list of the generated proposed ideas, means for setting detailed search conditions for the proposed ideas, means for performing further detailed analysis based on the set search conditions, and means for displaying specific periods, estimated amounts, and profitability. This makes it possible to generate and display profitable proposed ideas that take the user's emotions into consideration.

[0684] "Business name" is the name of a corporation or sole proprietorship.

[0685] "Industry" refers to the type of industry to which a business operator belongs.

[0686] "Required information" refers to information required to identify businesses and generate proposal ideas.

[0687] "Input information" refers to the business name, industry, and other necessary information that the user provides to the system.

[0688] A "data format" is input information converted into a form that is easy for a program to process.

[0689] "Grant Information" refers to detailed data about grants.

[0690] "Competitor Trends" is data that shows the activities and strategies of competitors in the market.

[0691] "Means of collecting data" refers to methods and technologies for obtaining subsidy information and competitor trends.

[0692] "Means for analyzing data" refers to the technology that processes collected data to generate useful proposal ideas.

[0693] "Proposed ideas" are specific initiatives that will increase profitability and efficiency for users.

[0694] An "emotion recognition engine" is a technology that analyzes a user's emotional state from their facial expressions and voice.

[0695] "Emotion data" is information about the user's emotional state obtained by an emotion recognition engine.

[0696] The "means for displaying proposed ideas" is a technique for visually presenting the generated proposed ideas in a format that can be confirmed by the user.

[0697] The "detailed search conditions" indicate the user's specific requirements and constraints for the proposed idea.

[0698] The "means for performing detailed analysis based on search conditions" is a technique for performing more specific data analysis based on detailed search conditions set by the user.

[0699] The "specific period" refers to the time required to implement the proposed idea.

[0700] The "estimated amount" is the budget amount required to implement the proposed idea.

[0701] "Profitability" refers to the revenue expected from implementing the proposed idea.

[0702] In this invention, the system operates in the following steps.

[0703] First, the user uses a tablet device to enter the business name, industry, and other necessary information. Specifically, they enter the company name, industry type (e.g., manufacturing), and specific project name (e.g., new product development). This information is converted into a data format and sent to the server in a standard format such as JSON. This ensures data consistency and integrity.

[0704] The server then uses multiple sources to gather data on grant information and competitor activity, including government APIs, industry news sites, and other trusted databases to obtain the latest information, using techniques such as API calls and web scraping.

[0705] The emotion recognition engine then analyzes the user's emotional state. The engine analyzes the user's facial expressions and voice data as they are inputting, recognizing their emotional state in real time. This emotional data is also sent to the server and used for analysis in the next step.

[0706] The collected data and sentiment data are analyzed using natural language processing (NLP) and machine learning (ML) algorithms. This generates profitable proposal ideas. For example, specific proposals such as utilizing digitalization promotion subsidies or developing cloud services for new products are considered. The generated proposal ideas are compiled into a list and sent to the device, where they are displayed to the user.

[0707] Users can set detailed search conditions for proposed ideas, such as region restrictions or budget limits. Based on the set search conditions, the server performs further detailed analysis. The detailed analysis includes determining whether or not subsidies can be used based on the newly set conditions, budget estimates, revenue forecasts, etc.

[0708] Finally, the server sends the results of the detailed analysis to the terminal, and the specific time frame, estimated cost, and profitability information are displayed to the user, providing them with specific and actionable suggestions for improving profitability and efficiency.

[0709] Hardware and Software Used

[0710] The hardware used mainly includes tablets and factory robots, while the software uses an emotion recognition engine (EmotionEngine), natural language processing and machine learning libraries (NLP and ML), and a REST API.

[0711] Specific examples

[0712] For example, a factory worker is searching for information on subsidies for a new product. When the worker uses a tablet to enter the necessary information, an emotion recognition engine analyzes the worker's emotional state, such as interest and stress level, from his facial expressions and voice. The server analyzes the collected subsidy information and competitive information and generates specific proposals such as "utilizing digitalization promotion subsidies." When the worker sets more detailed conditions for this proposal, the server performs detailed analysis, such as budget estimates and revenue forecasts, and displays the results.

[0713] Prompt Sentence Examples

[0714] You are an assistant tasked with generating proposal ideas that will contribute to improving factory productivity based on the information below. Please come up with ideas based on the information below.

[0715] Factory Information:

[0716] Business name: Y Co., Ltd.

[0717] Industry: Manufacturing

[0718] Process: New Product Development

[0719] Grant information: [JSON data of grant information]

[0720] Competitor Information: [JSON data of competitor information]

[0721] Worker emotional state: [JSON data of emotion data]

[0722] request:

[0723] Generate three proposal ideas.

[0724] For each proposal, explain the projected profitability.

[0725] View the list of suggestions.

[0726] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0727] Step 1:

[0728] The user uses a tablet device to enter the business name, industry, and other necessary information. This allows for the collection of corporate names, industry types, and specific project names such as new product development. The entered information is converted into a data format such as JSON and sent to the server. Input is done in text or multiple choice format, and the information converted into data format is output.

[0729] Step 2:

[0730] The server receives the submitted data and validates it for consistency and completeness. Data that passes the validation checks is used to collect data on grant information and competitor trends. The input is transformed JSON data and the output is a valid dataset.

[0731] Step 3:

[0732] The server uses government APIs, industry news sites, and other reliable databases to collect the latest grant information. It also collects competitors' technology and productivity improvement trends. This information is collected using API calls and web scraping. The input is the API key and web scraping settings, and the output is the latest grant information and competitor trends.

[0733] Step 4:

[0734] While the user is inputting, the emotion recognition engine analyzes the user's facial expression and voice data to recognize their emotional state in real time. This emotion data is also sent to the server and used for analysis in the next step. The input is the user's facial expression and voice data, and the output is the analyzed emotion data.

[0735] Step 5:

[0736] The server analyzes the collected grant information, competitive information, and user sentiment data. It uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas. Specific proposal ideas considered include "utilizing digitalization promotion subsidies" and "developing cloud services for new products." The input is the collected dataset and sentiment data, and the output is the generated proposal ideas.

[0737] Step 6:

[0738] The generated proposal ideas are compiled in list form and sent to the terminal. The user can check this and view the details of each proposal idea. The input is the generated proposal ideas, and the output is the proposal ideas compiled in list form.

[0739] Step 7:

[0740] Users input detailed search criteria for their proposed ideas, such as geographical restrictions or budget limits. The system uses an emotion recognition engine to suggest and adjust search criteria as needed. The input is the detailed search criteria set by the user, and the output is a dataset that reflects the detailed search criteria.

[0741] Step 8:

[0742] The server performs further detailed analysis based on the set detailed search conditions. Based on the newly set conditions, it determines whether or not subsidies can be used, estimates budgets, and predicts revenue. The input is the detailed search conditions, and the output is the results of the detailed analysis.

[0743] Step 9:

[0744] The server generates the results of the detailed analysis and sends them to the terminal. The user can then check the specific period, estimated amount, and profitability information. The input is the detailed analysis results, and the output is the specific period, estimated amount, and profitability information.

[0745] Through these processing steps, users can obtain specific and actionable suggestions for increasing profitability and efficiency.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] [Third embodiment]

[0750] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0751] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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).

[0756] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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."

[0762] The present invention is a system that includes a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and the trends of competitors, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability. A specific method for implementing this system is described below.

[0763] Step 1: User Input and Initial Settings

[0764] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0765] Step 2: Submit your input

[0766] The device sends the converted data format information to the server, which then prepares the data for analysis.

[0767] Step 3: Gathering grant information and competitor trends

[0768] The server collects data on the latest grant information and competitor trends from multiple sources (government grant information API, industry news sites, databases, etc.) The server efficiently obtains the required information using APIs and web scraping technology.

[0769] Step 4: Analyze the data and generate proposal ideas

[0770] The server analyzes the collected data and uses natural language processing and machine learning technologies to generate profitable proposal ideas based on the user's input, such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products."

[0771] Step 5: Listing the proposed ideas

[0772] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0773] Step 6: Setting advanced search criteria

[0774] The user selects ideas that interest them from the suggestions and sets detailed search conditions (e.g., region restrictions, budget limits, etc.). The device then sends these conditions back to the server.

[0775] Step 7: Detailed analysis

[0776] The server then performs further analysis based on the search criteria set by the user, specifically providing grant availability, budget estimates, and profitability forecasts for the selected proposal ideas.

[0777] Step 8: View detailed results

[0778] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0779] Specific examples

[0780] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. The server then analyzes this data and generates proposal ideas such as "utilizing the digitalization promotion subsidy" and "developing a cloud service for a new product." When the user selects "utilizing the digitalization promotion subsidy" and sets the detailed conditions, such as "region: Tokyo" and "maximum budget: 10 million yen," the server performs a detailed analysis based on this information and can provide information such as the specific implementation period, required budget, and projected profitability.

[0781] The processing flow will be explained below.

[0782] Step 1:

[0783] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0784] Step 2:

[0785] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0786] Step 3:

[0787] The server receives the JSON data sent from the device and prepares it for analysis.

[0788] Step 4:

[0789] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0790] Step 5:

[0791] The server analyzes the collected data and uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input.

[0792] Step 6:

[0793] The server compiles the generated proposal ideas into a list, including ideas such as "utilizing digitalization promotion subsidies" and "developing new product cloud services."

[0794] Step 7:

[0795] The server sends the list of proposed ideas to the terminal in JSON format, ensuring data integrity and security.

[0796] Step 8:

[0797] The terminal analyzes the list of proposed ideas received from the server and visually displays them, from which the user can select the proposed ideas that interest them.

[0798] Step 9:

[0799] Users can select specific proposal ideas and set detailed search conditions, such as "Region: Tokyo" or "Budget limit: 10 million yen."

[0800] Step 10:

[0801] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0802] Step 11:

[0803] The server receives the detailed search conditions and performs further detailed analysis, including determining whether or not grants can be used based on the newly set conditions, budget estimates, and revenue forecasts.

[0804] Step 12:

[0805] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0806] Step 13:

[0807] The terminal analyzes the detailed results received from the server and visually displays them for the user to review, including specific timeframes, estimated costs, and profitability information.

[0808] In this way, users can efficiently and effectively obtain proposal ideas that are likely to generate profits.

[0809] Example 1

[0810] 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."

[0811] Conventional systems limited the means by which business entities could efficiently collect information on subsidies and competitor trends and make effective proposals based on that information. Another issue was that the process of analyzing this information and presenting specific profit potential was complex and time-consuming. As a result, it took time and effort for business entities to find the optimal proposal. To solve these problems, a system was needed that integrated and streamlined the processes of collection, analysis, proposal generation, and presentation.

[0812] 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.

[0813] In this invention, the server includes means for inputting the business entity name, business type, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing further detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profit potential, and means for expanding the scope of application using a generative AI model and prompt text. This enables business entities to efficiently collect and analyze the necessary information and easily generate and confirm optimal proposals.

[0814] "Entity name" refers to the official name of a company or organization.

[0815] "Type of business" refers to the type of activity or business conducted by a company or organization.

[0816] "Other necessary information" refers to any additional details required by the system other than the name of the business entity and type of business.

[0817] A "data format" refers to a format for storing and transmitting information digitally. Examples include JSON and XML.

[0818] "Grant Information" refers to information regarding financial assistance provided by government or private sources.

[0819] "Competitor trends" refers to the current activities and market movements of competing companies.

[0820] "Data collection method" refers to the technology or method used by the server to obtain the required information, such as an API call or web scraping.

[0821] "Data analysis tools" refers to techniques and methods for processing collected data and extracting meaningful information. Examples include natural language processing and machine learning.

[0822] "Proposal Ideas" refers to specific plans and strategies for increasing profitability and efficiency of business entities, which are generated based on collected and analyzed data.

[0823] "List display means" refers to a technique or method for visually displaying the generated proposed ideas.

[0824] "Advanced search conditions" refers to search criteria used to narrow down proposed ideas to those that meet specific conditions.

[0825] "Detailed analysis means" refers to techniques and methods for conducting deeper analysis based on detailed search conditions.

[0826] "Specific period" refers to the time or period required to implement the proposed idea.

[0827] "Estimated amount" refers to the budget and expenses required to implement the proposed idea.

[0828] "Profit potential" refers to an indicator that shows how much revenue a proposed idea has the potential to generate.

[0829] "Generative AI model" refers to artificial intelligence techniques or machine learning models used to analyze data and generate meaningful information or recommendations.

[0830] A "prompt sentence" refers to an instruction or inquiry sentence to be input into a generative AI model.

[0831] This invention is a system that efficiently collects and analyzes the information necessary for businesses and organizations (hereinafter referred to as "business entities") to receive support, and generates proposals. This system allows businesses to easily find optimal grant and market opportunities and develop strategies to increase revenue.

[0832] Hardware and software used

[0833] Terminal: A device used by a user to enter the name of the business, type of business, and other necessary information. Examples include a personal computer or smartphone.

[0834] Server: The central processing unit that collects data, analyzes it, and generates recommendations. It can be a cloud-based server or a dedicated server.

[0835] Software: Natural language processing (NLP) libraries (e.g., SpaCy, NLTK), machine learning frameworks (e.g., scikit-learn, TensorFlow), scraping tools for data collection (e.g., BeautifulSoup, Scrapy), libraries for API connectivity (e.g., Requests).

[0836] Program processing flow

[0837] First, the user uses a terminal to input the business entity name (e.g., "Y Corporation"), business type (e.g., "manufacturing"), and other necessary information (e.g., "new product development"). The terminal collects this information and converts it into a standard data format such as JSON. Specifically, it uses JavaScript or Python functions to convert the data into JSON format.

[0838] The terminal then sends the converted data to the server using an HTTP POST request. The server receives the data and stores it in a database. The server then collects the necessary information from government grant information APIs, news websites, and industry databases. The API requests are sent using Python's Requests library, and the resulting data is received in JSON format. Web scraping can also be performed using BeautifulSoup or Scrapy.

[0839] The collected data is analyzed on a server. At this time, natural language processing technology (SpaCy, NLTK) and machine learning technology (scikit-learn, TensorFlow) are used to generate proposed ideas based on the information entered by the user. For example, if a business is in the manufacturing industry, proposals such as "utilizing digitalization promotion subsidies" or "utilizing new product development support programs" may be generated.

[0840] The server compiles the generated proposal ideas into a list and sends it to the terminal as an HTTP response. The terminal receives this and displays it on the screen in an easy-to-read format for the user. The user selects the proposals that interest them from the list and sets detailed search conditions (e.g., region "Tokyo" and upper budget limit "10 million yen"). The settings are sent back to the server, which performs further detailed analysis.

[0841] The server completes the detailed analysis and generates results including specific timeframes, estimated amounts, and profit potential, which are sent in JSON format to the terminal, which then displays them visually to the user.

[0842] Specific examples

[0843] For example, consider a case where a user is searching for a proposal idea that is likely to generate revenue for a manufacturing business entity, "Y Co., Ltd." The user enters the business entity name, "Y Co., Ltd.", the business type, "manufacturing," and "new product development" into a terminal. The terminal converts this data into JSON format and sends it to the server via an HTTP POST request. The server receives this and collects the latest information from grant information APIs and news websites. The server then uses natural language processing and machine learning techniques to generate proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services for new products."

[0844] The generated proposal ideas are sent in list form to the device, which displays them to the user. When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 10 million yen," the device resends this to the server, which performs a detailed analysis. Finally, the user is provided with information such as the specific project period, required budget, and projected profitability.

[0845] Prompt Sentence Examples

[0846] Enter the following prompt into the generative AI model:

[0847] "The business name is 'Y Co., Ltd.', the business type is 'manufacturing', and the required information is 'new product development'. Please collect the latest subsidy information and competitor trends, and generate proposal ideas that are expected to generate profits based on that information. Display the generated idea list and allow the user to set detailed conditions."

[0848] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0849] Step 1:

[0850] The user uses the device to enter the business entity name, type of business, and other necessary information. Specifically, the user operates the keyboard or touch panel to enter information such as "Y Co., Ltd.", "manufacturing industry," and "new product development." The entered data is converted to JSON format within the device. For example, the data can be converted to JSON format using the JavaScript JSON.stringify() function.

[0851] Input: Name of business entity, type of business, other necessary information

[0852] Output: Input data in JSON format

[0853] Step 2:

[0854] The terminal sends the converted JSON data to the server. Specifically, the data is sent using an HTTP POST request. The data sent from the terminal is received by the server. The received data is stored in a database.

[0855] Input: Input data in JSON format

[0856] Output: Send data to the server, store data in the database on the server

[0857] Step 3:

[0858] The server uses the collected database to gather information on grants and competitor trends, specifically by using API connections and web scraping. For example, it uses the Requests and BeautifulSoup libraries to gather information from government grant information APIs and industry news sites.

[0859] Input: Data stored in the database on the server

[0860] Output: Subsidy information and competitor trends data

[0861] Step 4:

[0862] The server analyzes the collected data and generates proposal ideas. Specifically, it analyzes the data using natural language processing (NLP) and machine learning models (generative AI models). For example, it uses Scikit-learn and TensorFlow to generate proposals that are beneficial to the business. It creates specific proposal ideas such as "utilizing digitalization promotion subsidies" and "utilizing new product development support programs."

[0863] Input: Grant information and competitor trends data

[0864] Output: Proposed Idea

[0865] Step 5:

[0866] The server compiles the generated proposal ideas into a list and converts it into JSON format. It then sends this to the device using an HTTP response. The device then visually displays the received data to the user using HTML and JavaScript. For example, it displays a list so that the user can easily click to see the details.

[0867] Input: Proposed idea

[0868] Output: A list of proposed ideas sent to the device

[0869] Step 6:

[0870] The user selects ideas that interest them from the suggestions and sets detailed search criteria. For example, they can use drop-down menus and radio buttons to set "Region: Tokyo" and "Budget limit: 10 million yen." The search criteria are then converted back to JSON format and sent to the server using an HTTP POST request.

[0871] Input: Selected proposal idea and detailed search criteria

[0872] Output: Detailed search criteria data in JSON format

[0873] Step 7:

[0874] The server then performs further analysis based on the received search criteria data, such as determining the availability of grants, budget estimates, and profitability forecasts for the selected proposals, by making additional database queries or API requests.

[0875] Input: Detailed search criteria data

[0876] Output: Detailed analysis result data

[0877] Step 8:

[0878] The server converts the detailed analysis results data into JSON format and sends it to the terminal as an HTTP response. The terminal then visually displays the received data to the user using HTML and JavaScript. Specifically, it uses tables and graphs to display detailed results such as specific periods, estimated amounts, and predicted profitability.

[0879] Input: Detailed analysis result data

[0880] Output: Detailed results displayed on the terminal

[0881] (Application example 1)

[0882] 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."

[0883] In conventional logistics centers, data collection on subsidy information and competitor trends is rare, resulting in the problem that formulating an efficient operation strategy takes time and effort. Furthermore, data analysis is insufficient, making it difficult to generate profitable proposal ideas.

[0884] 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.

[0885] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profitability, and means for collecting operational data of the logistics center and proposing strategies for improving efficiency. This makes it possible to formulate an efficient and profitable operational strategy for the logistics center.

[0886] A "business name" is a name used to identify a particular company or organization.

[0887] "Industry" is a category that indicates the classification of a particular industry or business activity.

[0888] A "requirement" is an item of information or data that is essential for the operation of a system or process.

[0889] A "data format" is a format that organizes and structures information in a particular way.

[0890] "Funding Information" means information about funding support or grants provided by governments or other agencies.

[0891] "Competitor activity" is information about the recent activities and strategies of other companies or organizations competing in the same industry.

[0892] "Collection" is the act of gathering necessary data and information.

[0893] "Analysis" is the process of analyzing collected data and information in detail to derive meaning and patterns.

[0894] A "proposal idea" is a concept of a specific plan or strategy for achieving a specific goal.

[0895] "List display" refers to the act of presenting the generated proposed ideas and information to the user in list form.

[0896] "Detailed search conditions" are conditions for obtaining more specific information based on the user's needs.

[0897] "Detailed analysis" is the process of conducting a deeper level of data analysis based on the results of the initial analysis.

[0898] A "period" is a time frame that indicates the duration of a particular activity or project.

[0899] "Estimate" means the projected cost required to carry out a particular project or activity.

[0900] "Profitability" is a measure of how much profit a particular activity or project generates.

[0901] A "logistics center" is a base for storing, distributing, and managing goods.

[0902] "Operational data" refers to information and statistics about the operating status of a particular system or process.

[0903] An efficiency improvement strategy is a plan to improve and optimize the performance of existing processes and systems.

[0904] "Natural language processing" is a technology that allows computers to understand, interpret, and generate human language.

[0905] "Machine learning" is a branch of artificial intelligence in which algorithms improve themselves based on data.

[0906] A "generative AI model" is an artificial intelligence model that can generate new content and predictions based on data.

[0907] A "prompt" is text that is input to a generative AI model and serves to guide the output that the model generates.

[0908] This invention is a system for proposing strategies to improve efficiency in a logistics center. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0909] First, the user uses a terminal to input the company name, industry, and other necessary information. For example, they provide information such as "Company A," "Logistics industry," and "Improvement of transportation efficiency." This information is converted into a data format (e.g., JSON format).

[0910] The converted data is sent from the device to a server, which collects the latest grant information and competitor trends from multiple sources (subsidy information APIs, industry news sites, databases, etc.) using APIs and web scraping technology.

[0911] The collected data is analyzed using natural language processing (NLP) and machine learning (ML) techniques. During the analysis, a generative AI model is used to generate profitable proposal ideas based on user input. For example, it may suggest "optimizing transportation routes" or "introducing a new delivery system."

[0912] The generated proposal ideas are compiled into a list and sent to the device. The user can review this and select the proposal ideas they are interested in. By setting detailed search conditions (e.g., region restrictions, budget limits), the device will again send the conditions to the server.

[0913] The server then performs a more detailed analysis based on the search criteria. Specifically, it calculates the availability of grant funds, budget estimates, and profitability forecasts for the selected proposal ideas. The results of the detailed analysis are sent to the device, where specific information such as the time frame, estimated amount, and profitability are displayed.

[0914] For example, if a user selects "Transportation Route Optimization" for "Company A" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 5 million yen," the server will perform a detailed analysis based on this and provide information such as the specific duration of the initiative, the required budget, and projected profitability.

[0915] An example of a prompt is:

[0916] "A company that operates Logistics Center A is aiming to improve transportation efficiency. Based on information about subsidies and the situation of competitors, please generate profitable proposal ideas and present a specific implementation period and estimated costs."

[0917] This system will enable logistics centers to develop efficient and profitable operational strategies.

[0918] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0919] Step 1:

[0920] The user uses the terminal to input the business name, industry, and other necessary information. For example, they provide information such as "Company A," "logistics industry," and "improved transport efficiency." The terminal then converts this information into JSON format. The input includes the data entered by the user, such as "Company A," "logistics industry," and "improved transport efficiency," and the output is the data converted into JSON format.

[0921] Step 2:

[0922] The terminal sends the converted JSON-formatted data to the server. The server saves the received data in preparation for analysis. Specifically, the terminal sends the JSON data as an HTTP POST request, and the server saves the received data in a database. The input is the JSON data sent from the terminal, and the output is in the format saved in the database on the server.

[0923] Step 3:

[0924] The server collects data on grant information and competitor trends from multiple sources (e.g., grant information APIs, industry news sites, and databases). This collection is done using API requests and web scraping techniques. For example, grant information is obtained by sending an API request, and competitor trends are collected by web scraping. The input is the API request or scraping URL from the server, and the output is the obtained grant information and competitor trend data.

[0925] Step 4:

[0926] The server analyzes the collected data using natural language processing (NLP) and machine learning (ML) techniques and generates proposed ideas using a generative AI model. For example, it analyzes grant information and industry news to generate efficiency improvement strategies tailored to the user's needs. The input is the collected grant information and competitor trends data, and the output is a list of generated proposed ideas.

[0927] Step 5:

[0928] The generated proposed ideas are compiled into a list and sent to the device. The device displays the received data on the screen. Specifically, the server sends the proposed idea list to the device in JSON format, which the device parses and displays in a format that is easy for the user to check. The input is the proposed idea list data sent from the server, and the output is the data displayed on the screen.

[0929] Step 6:

[0930] The user selects the proposal ideas that interest them using their device and sets detailed search conditions (e.g., region restriction, budget limit). For example, they enter conditions such as "region: Tokyo" and "budget limit: 5 million yen." The input is the detailed search conditions set by the user, and the output is data converted from those conditions into JSON format.

[0931] Step 7:

[0932] The device sends the set search criteria to the server, which then performs more detailed analysis based on the received criteria. For example, it may determine the availability of subsidies, estimate the budget, or predict profitability. The input is the data for the detailed search criteria sent from the device, and the output is the data of the analysis results.

[0933] Step 8:

[0934] The server generates the results of the detailed analysis and sends them to the terminal. The terminal displays the received data on the screen so that the user can check it. For example, it displays a list of specific time periods, estimated amounts, and profitability information. The input is the data of the detailed analysis results sent from the server, and the output is the specific time period, estimated amounts, and profitability information displayed on the screen.

[0935] 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.

[0936] The present invention provides a system including a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and competitor trends, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability.In addition, by combining this with an emotion engine that recognizes the user's emotions, the system achieves an even more advanced user experience.

[0937] Step 1: User Input and Initial Settings

[0938] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[0939] Step 2: Submit your input

[0940] The terminal sends the converted data format information to the server, where a validation check is performed to ensure the data is complete and consistent.

[0941] Step 3: Gathering grant information and competitor trends

[0942] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0943] Step 4: Analyze user emotions with the emotion engine

[0944] The emotion engine analyzes facial expressions and voice data while the user is typing or operating the device, and recognizes the user's emotional state in real time. This emotional data is also sent to the server and used for analysis.

[0945] Step 5: Analyze the data and generate proposal ideas

[0946] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it considers ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0947] Step 6: Listing the proposed ideas

[0948] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0949] Step 7: Setting advanced search criteria

[0950] Users select ideas that interest them and set detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0951] Step 8: Detailed analysis

[0952] The server then performs a more detailed analysis based on the search criteria set by the user, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts.

[0953] Step 9: View detailed results

[0954] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[0955] Specific examples

[0956] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. Furthermore, the emotion engine analyzes the user's emotions from their facial expressions and voice while they are entering information, and their emotional state is also sent as data to the server.

[0957] The server analyzes this data and generates proposal ideas such as "Utilizing the Digitalization Promotion Subsidy" and "Deploying a new product as a cloud service." When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets detailed conditions such as "Region: Tokyo" and "Budget Limit: 10 million yen," the server performs a detailed analysis based on this and provides information such as the specific implementation period, required budget, and projected profitability. The user's emotional state is also continuously monitored, allowing for interactive responses tailored to the displayed results.

[0958] The processing flow will be explained below.

[0959] Step 1:

[0960] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[0961] Step 2:

[0962] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[0963] Step 3:

[0964] The device sends the user's facial expressions and voice to the emotion engine in real time to collect the user's emotional data. The emotion engine analyzes the emotional data and identifies the user's emotional state. This emotional data is also converted into JSON format and sent to the server.

[0965] Step 4:

[0966] The server receives the JSON data (input information and emotion data) sent from the device and prepares it for analysis.

[0967] Step 5:

[0968] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[0969] Step 6:

[0970] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it could suggest ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[0971] Step 7:

[0972] The server generates a list of proposed ideas and sends it to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[0973] Step 8:

[0974] The user selects the ideas they are interested in from the suggestions and sets detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[0975] Step 9:

[0976] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[0977] Step 10:

[0978] The server receives the detailed search conditions and emotion data and performs further detailed analysis, including determining whether or not to use subsidies based on the newly set conditions, estimating budgets, and forecasting revenue.

[0979] Step 11:

[0980] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[0981] Step 12:

[0982] The device analyzes the detailed results received from the server and visually displays them for the user to review. The display includes specific timeframes, estimated amounts, and profitability information. The emotion engine continuously monitors the user's emotions and provides interactive responses tailored to the displayed results.

[0983] Step 13:

[0984] The user reviews the detailed results presented and makes a final decision. The emotion engine analyzes the user's emotional state and provides appropriate advice and guidance when support is required.

[0985] Example 2

[0986] 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."

[0987] In today's business environment, companies need to quickly and accurately grasp a wide range of information, such as subsidy information and competitor trends. They also need to generate specific proposal ideas and create detailed, actionable plans based on this information. However, existing systems often take time to collect and analyze large amounts of data and are unable to provide interactive responses that take into account the user's emotional state. This makes it difficult for companies to receive the appropriate support at the right time.

[0988] 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.

[0989] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for analyzing the user's emotions using an emotion recognition engine and transmitting the emotion data to the server, and means for displaying the specific period, estimated amount, and profitability. This allows users to quickly and accurately obtain proposal ideas, and further enables interactive and individual responses through real-time emotion analysis.

[0990] "Business name" refers to the name of a company or organization.

[0991] "Industry" refers to the type or category of business conducted by a company or organization.

[0992] "Requirements" refers to items of information that a user must enter in order for the system to function properly.

[0993] "Input information" refers to the collection of data that a user provides to a system.

[0994] "Data format" refers to a particular format for structuring information.

[0995] "Subsidy information" refers to information about various subsidies that companies and organizations can apply for.

[0996] "Competitors" refers to other companies or organizations in the same market or industry that offer similar products or services.

[0997] "Trends" refers to current trends and changes in a market or industry.

[0998] "Means of collecting data" refers to the mechanisms and tools used to obtain the necessary information.

[0999] "Means of analysis" refers to the mechanisms and methods for analyzing and processing collected data.

[1000] "Proposed Ideas" refers to specific action plans that are generated based on the collected and analyzed information.

[1001] The "means for displaying a list" refers to a method for visually presenting the generated proposed ideas to the user.

[1002] "Advanced search conditions" refer to conditions set by the user to further narrow down the proposed ideas.

[1003] An "emotion recognition engine" refers to technology for analyzing a user's emotional state in real time.

[1004] The "specific period" refers to the period during which the action to be taken is to be carried out.

[1005] "Estimated Amount" refers to an estimate of the costs required to implement the proposed idea.

[1006] "Profitability" refers to an indicator that evaluates the economic benefits that a proposed idea brings.

[1007] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[1008] "Machine learning" refers to a technology that analyzes data, automatically learns, and makes predictions and judgments.

[1009] A "structured data format" refers to a data format that is organized based on specific rules.

[1010] The present invention provides a system that enables companies and businesses to quickly provide optimal subsidy information and specific proposal ideas, and also enables interactive responses that take into account the emotional state of the user. Specific embodiments of the system are described below.

[1011] First, the user uses the terminal to enter the company name, industry, and other necessary information. For example, if the entered information is "X Corporation," "manufacturing," and "new product development," the terminal collects this information and converts it into a data format such as JSON. The terminal then sends the converted data to the server. At this time, the terminal performs a validation check to ensure the data is complete and consistent.

[1012] Based on the received data, the server collects data on the latest grant information and competitor trends from multiple sources, specifically using API calls and web scraping techniques to obtain information from government grant APIs, industry news sites, etc. The collected data is then stored in an internal database.

[1013] Furthermore, an emotion recognition engine is used to analyze the user's emotions. While the user is typing or operating the device, facial expressions and voice data are captured using a webcam and microphone, and an analysis algorithm is used to recognize the user's emotional state. This emotional data is sent to the server and used for subsequent analysis.

[1014] The server analyzes the collected data and emotional data. Specifically, it applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" are considered.

[1015] The generated proposal ideas are sent from the server to the device, which displays them in list form to the user. The user selects the proposal ideas that interest them from the displayed list and sets detailed search conditions (e.g., "Area limited: Tokyo," "Budget limit: 10 million yen"). The emotion recognition engine analyzes changes in the user's emotions and suggests or adjusts search conditions as necessary.

[1016] The server then performs a more detailed analysis based on the search criteria that was set, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts. The detailed analysis results generated by the server are sent to the terminal, and specific information on the period, estimated amount, and profitability is presented to the user.

[1017] For example, when a user enters "X Corporation," "manufacturing," and "new product development," the device converts this into JSON format, resulting in something like "{ 'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The device then sends this data to the server, which uses government_grants_api and industry_news_scraper to collect information on grants and competitor trends. The acquired data is analyzed, and proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services" are generated.

[1018] (Example of a specific prompt sentence)

[1019] "Please tell me about digitalization subsidies related to new product development in the manufacturing industry. The specific conditions are that they are limited to Tokyo and have a budget cap of 10 million yen."

[1020] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1021] Step 1:

[1022] The user uses the terminal to enter the company name, industry, and other necessary information. For example, they might enter information such as "X Corporation, manufacturing, new product development." The terminal receives this input information and converts it into a data format such as JSON. Specific input data is text information such as "X Corporation" and "manufacturing," which is converted into structured data such as "{'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The converted data is then ready to be sent to the server.

[1023] Step 2:

[1024] The terminal sends the information in the converted data format to the server. At this time, the terminal performs a validation check to maintain the completeness and consistency of the data. Specifically, it checks whether the input data is missing or is in the correct format. For example, it checks whether the company name "X Co., Ltd." is in the correct format and whether the industry is within the options. Once the check is complete, the data is sent to the server via an HTTP request. The server checks the contents of the received data and proceeds with the next process.

[1025] Step 3:

[1026] The server collects data on grant information and competitor trends from multiple sources. Specifically, it calls government grant APIs and web scrapes industry news sites. This process involves sending requests to API endpoints to obtain grant information in JSON format. It also uses web scraping tools to obtain competitor news articles and analytical reports. The collected data is stored in the server's internal database. This allows it to accumulate the latest grant information and competitor trends.

[1027] Step 4:

[1028] An emotion recognition engine analyzes facial and voice data while the user is typing or operating the device to recognize the user's emotional state. For example, a webcam or microphone can be used to capture the user's facial expressions and tone of voice. This data is analyzed in real time to identify the user's emotional state (e.g., joy, surprise, distress, etc.). This emotional data is also sent to the server and used as material for analysis along with other data.

[1029] Step 5:

[1030] The server performs analysis using the collected data and emotional data. It then applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's needs and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" may be generated. The server then compiles these proposal ideas into a list and records the selection process. This allows the server to verify that the generated proposal ideas are based on concrete evidence.

[1031] Step 6:

[1032] The generated proposal ideas are sent to the device. The device receives them and displays them on the screen in list format so that the user can easily check them. For example, each proposal idea can be presented in an easy-to-understand card format, with links and buttons for the user to view the details. This list-format proposal display allows the user to compare and select at a glance.

[1033] Step 7:

[1034] Users select proposal ideas that interest them from a list and set detailed search criteria. For example, they can enter regional restrictions (e.g., "Tokyo") or budget limits (e.g., "10 million yen"). While they are entering their search criteria, the emotion recognition engine analyzes the user's emotional changes and makes appropriate suggestions or adjustments. The input data based on the detailed search criteria is sent to the server, where further detailed analysis begins.

[1035] Step 8:

[1036] The server performs further detailed analysis based on the set search criteria. Based on the newly set criteria, it determines whether grants are available, estimates budgets, and forecasts revenue. It uses data analysis tools to generate detailed reports, such as "subsidies available based on local conditions," recommended "budget plans," and "projected profitability." The analysis results are prepared for the next step.

[1037] Step 9:

[1038] The server generates detailed analysis results and sends them to the terminal, which then displays specific information on the duration, estimated cost, and profitability. The terminal then receives this information and displays it on the screen in a format that is easy for the user to understand. For example, presenting information using visual elements, such as a Gantt chart showing the project duration or a bar chart showing a comparison of costs and profitability, helps users understand the information better.

[1039] In this way, the system can effectively carry out a series of processes from user input to providing detailed analysis results.

[1040] (Application example 2)

[1041] 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."

[1042] This invention aims to improve productivity in factories by analyzing the latest subsidy information and competitor trends to generate and display specific and profitable proposal ideas, thereby solving the problem of realizing an efficient manufacturing process. It is also required to increase user satisfaction and interest by taking into account the user's emotional state.

[1043] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the name of the business, type of business, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposed ideas, means for analyzing the user's emotional state using an emotion recognition engine and transmitting the data, means for displaying a list of the generated proposed ideas, means for setting detailed search conditions for the proposed ideas, means for performing further detailed analysis based on the set search conditions, and means for displaying specific periods, estimated amounts, and profitability. This makes it possible to generate and display profitable proposed ideas that take the user's emotions into consideration.

[1044] "Business name" is the name of a corporation or sole proprietorship.

[1045] "Industry" refers to the type of industry to which a business operator belongs.

[1046] "Required information" refers to information required to identify businesses and generate proposal ideas.

[1047] "Input information" refers to the business name, industry, and other necessary information that the user provides to the system.

[1048] A "data format" is input information converted into a form that is easy for a program to process.

[1049] "Grant Information" refers to detailed data about grants.

[1050] "Competitor Trends" is data that shows the activities and strategies of competitors in the market.

[1051] "Means of collecting data" refers to methods and technologies for obtaining subsidy information and competitor trends.

[1052] "Means for analyzing data" refers to the technology that processes collected data to generate useful proposal ideas.

[1053] "Proposed ideas" are specific initiatives that will increase profitability and efficiency for users.

[1054] An "emotion recognition engine" is a technology that analyzes a user's emotional state from their facial expressions and voice.

[1055] "Emotion data" is information about the user's emotional state obtained by an emotion recognition engine.

[1056] The "means for displaying proposed ideas" is a technique for visually presenting the generated proposed ideas in a format that can be confirmed by the user.

[1057] The "detailed search conditions" indicate the user's specific requirements and constraints for the proposed idea.

[1058] The "means for performing detailed analysis based on search conditions" is a technique for performing more specific data analysis based on detailed search conditions set by the user.

[1059] The "specific period" refers to the time required to implement the proposed idea.

[1060] The "estimated amount" is the budget amount required to implement the proposed idea.

[1061] "Profitability" refers to the revenue expected from implementing the proposed idea.

[1062] In this invention, the system operates in the following steps.

[1063] First, the user uses a tablet device to enter the business name, industry, and other necessary information. Specifically, they enter the company name, industry type (e.g., manufacturing), and specific project name (e.g., new product development). This information is converted into a data format and sent to the server in a standard format such as JSON. This ensures data consistency and integrity.

[1064] The server then uses multiple sources to gather data on grant information and competitor activity, including government APIs, industry news sites, and other trusted databases to obtain the latest information, using techniques such as API calls and web scraping.

[1065] The emotion recognition engine then analyzes the user's emotional state. The engine analyzes the user's facial expressions and voice data as they are inputting, recognizing their emotional state in real time. This emotional data is also sent to the server and used for analysis in the next step.

[1066] The collected data and sentiment data are analyzed using natural language processing (NLP) and machine learning (ML) algorithms. This generates profitable proposal ideas. For example, specific proposals such as utilizing digitalization promotion subsidies or developing cloud services for new products are considered. The generated proposal ideas are compiled into a list and sent to the device, where they are displayed to the user.

[1067] Users can set detailed search conditions for proposed ideas, such as region restrictions or budget limits. Based on the set search conditions, the server performs further detailed analysis. The detailed analysis includes determining whether or not subsidies can be used based on the newly set conditions, budget estimates, revenue forecasts, etc.

[1068] Finally, the server sends the results of the detailed analysis to the terminal, and the specific time frame, estimated cost, and profitability information are displayed to the user, providing them with specific and actionable suggestions for improving profitability and efficiency.

[1069] Hardware and Software Used

[1070] The hardware used mainly includes tablets and factory robots, while the software uses an emotion recognition engine (EmotionEngine), natural language processing and machine learning libraries (NLP and ML), and a REST API.

[1071] Specific examples

[1072] For example, a factory worker is searching for information on subsidies for a new product. When the worker uses a tablet to enter the necessary information, an emotion recognition engine analyzes the worker's emotional state, such as interest and stress level, from his facial expressions and voice. The server analyzes the collected subsidy information and competitive information and generates specific proposals such as "utilizing digitalization promotion subsidies." When the worker sets more detailed conditions for this proposal, the server performs detailed analysis, such as budget estimates and revenue forecasts, and displays the results.

[1073] Prompt Sentence Examples

[1074] You are an assistant tasked with generating proposal ideas that will contribute to improving factory productivity based on the information below. Please come up with ideas based on the information below.

[1075] Factory Information:

[1076] Business name: Y Co., Ltd.

[1077] Industry: Manufacturing

[1078] Process: New Product Development

[1079] Grant information: [JSON data of grant information]

[1080] Competitor Information: [JSON data of competitor information]

[1081] Worker emotional state: [JSON data of emotion data]

[1082] request:

[1083] Generate three proposal ideas.

[1084] For each proposal, explain the projected profitability.

[1085] View the list of suggestions.

[1086] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1087] Step 1:

[1088] The user uses a tablet device to enter the business name, industry, and other necessary information. This allows for the collection of corporate names, industry types, and specific project names such as new product development. The entered information is converted into a data format such as JSON and sent to the server. Input is done in text or multiple choice format, and the information converted into data format is output.

[1089] Step 2:

[1090] The server receives the submitted data and validates it for consistency and completeness. Data that passes the validation checks is used to collect data on grant information and competitor trends. The input is transformed JSON data and the output is a valid dataset.

[1091] Step 3:

[1092] The server uses government APIs, industry news sites, and other reliable databases to collect the latest grant information. It also collects competitors' technology and productivity improvement trends. This information is collected using API calls and web scraping. The input is the API key and web scraping settings, and the output is the latest grant information and competitor trends.

[1093] Step 4:

[1094] While the user is inputting, the emotion recognition engine analyzes the user's facial expression and voice data to recognize their emotional state in real time. This emotion data is also sent to the server and used for analysis in the next step. The input is the user's facial expression and voice data, and the output is the analyzed emotion data.

[1095] Step 5:

[1096] The server analyzes the collected grant information, competitive information, and user sentiment data. It uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas. Specific proposal ideas considered include "utilizing digitalization promotion subsidies" and "developing cloud services for new products." The input is the collected dataset and sentiment data, and the output is the generated proposal ideas.

[1097] Step 6:

[1098] The generated proposal ideas are compiled in list form and sent to the terminal. The user can check this and view the details of each proposal idea. The input is the generated proposal ideas, and the output is the proposal ideas compiled in list form.

[1099] Step 7:

[1100] Users input detailed search criteria for their proposed ideas, such as geographical restrictions or budget limits. The system uses an emotion recognition engine to suggest and adjust search criteria as needed. The input is the detailed search criteria set by the user, and the output is a dataset that reflects the detailed search criteria.

[1101] Step 8:

[1102] The server performs further detailed analysis based on the set detailed search conditions. Based on the newly set conditions, it determines whether or not subsidies can be used, estimates budgets, and predicts revenue. The input is the detailed search conditions, and the output is the results of the detailed analysis.

[1103] Step 9:

[1104] The server generates the results of the detailed analysis and sends them to the terminal. The user can then check the specific period, estimated amount, and profitability information. The input is the detailed analysis results, and the output is the specific period, estimated amount, and profitability information.

[1105] Through these processing steps, users can obtain specific and actionable suggestions for increasing profitability and efficiency.

[1106] 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.

[1107] 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.

[1108] 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.

[1109] [Fourth embodiment]

[1110] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1111] 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.

[1112] 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).

[1113] 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.

[1114] 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.

[1115] 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).

[1116] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1117] 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.

[1118] 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.

[1119] 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.

[1120] 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.

[1121] 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.

[1122] 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."

[1123] The present invention is a system that includes a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and the trends of competitors, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability. A specific method for implementing this system is described below.

[1124] Step 1: User Input and Initial Settings

[1125] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[1126] Step 2: Submit your input

[1127] The device sends the converted data format information to the server, which then prepares the data for analysis.

[1128] Step 3: Gathering grant information and competitor trends

[1129] The server collects data on the latest grant information and competitor trends from multiple sources (government grant information API, industry news sites, databases, etc.) The server efficiently obtains the required information using APIs and web scraping technology.

[1130] Step 4: Analyze the data and generate proposal ideas

[1131] The server analyzes the collected data and uses natural language processing and machine learning technologies to generate profitable proposal ideas based on the user's input, such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products."

[1132] Step 5: Listing the proposed ideas

[1133] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[1134] Step 6: Setting advanced search criteria

[1135] The user selects ideas that interest them from the suggestions and sets detailed search conditions (e.g., region restrictions, budget limits, etc.). The device then sends these conditions back to the server.

[1136] Step 7: Detailed analysis

[1137] The server then performs further analysis based on the search criteria set by the user, specifically providing grant availability, budget estimates, and profitability forecasts for the selected proposal ideas.

[1138] Step 8: View detailed results

[1139] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[1140] Specific examples

[1141] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. The server then analyzes this data and generates proposal ideas such as "utilizing the digitalization promotion subsidy" and "developing a cloud service for a new product." When the user selects "utilizing the digitalization promotion subsidy" and sets the detailed conditions, such as "region: Tokyo" and "maximum budget: 10 million yen," the server performs a detailed analysis based on this information and can provide information such as the specific implementation period, required budget, and projected profitability.

[1142] The processing flow will be explained below.

[1143] Step 1:

[1144] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[1145] Step 2:

[1146] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[1147] Step 3:

[1148] The server receives the JSON data sent from the device and prepares it for analysis.

[1149] Step 4:

[1150] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[1151] Step 5:

[1152] The server analyzes the collected data and uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input.

[1153] Step 6:

[1154] The server compiles the generated proposal ideas into a list, including ideas such as "utilizing digitalization promotion subsidies" and "developing new product cloud services."

[1155] Step 7:

[1156] The server sends the list of proposed ideas to the terminal in JSON format, ensuring data integrity and security.

[1157] Step 8:

[1158] The terminal analyzes the list of proposed ideas received from the server and visually displays them, from which the user can select the proposed ideas that interest them.

[1159] Step 9:

[1160] Users can select specific proposal ideas and set detailed search conditions, such as "Region: Tokyo" or "Budget limit: 10 million yen."

[1161] Step 10:

[1162] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[1163] Step 11:

[1164] The server receives the detailed search conditions and performs further detailed analysis, including determining whether or not grants can be used based on the newly set conditions, budget estimates, and revenue forecasts.

[1165] Step 12:

[1166] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[1167] Step 13:

[1168] The terminal analyzes the detailed results received from the server and visually displays them for the user to review, including specific timeframes, estimated costs, and profitability information.

[1169] In this way, users can efficiently and effectively obtain proposal ideas that are likely to generate profits.

[1170] Example 1

[1171] 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."

[1172] Conventional systems limited the means by which business entities could efficiently collect information on subsidies and competitor trends and make effective proposals based on that information. Another issue was that the process of analyzing this information and presenting specific profit potential was complex and time-consuming. As a result, it took time and effort for business entities to find the optimal proposal. To solve these problems, a system was needed that integrated and streamlined the processes of collection, analysis, proposal generation, and presentation.

[1173] 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.

[1174] In this invention, the server includes means for inputting the business entity name, business type, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing further detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profit potential, and means for expanding the scope of application using a generative AI model and prompt text. This enables business entities to efficiently collect and analyze the necessary information and easily generate and confirm optimal proposals.

[1175] "Entity name" refers to the official name of a company or organization.

[1176] "Type of business" refers to the type of activity or business conducted by a company or organization.

[1177] "Other necessary information" refers to any additional details required by the system other than the name of the business entity and type of business.

[1178] A "data format" refers to a format for storing and transmitting information digitally. Examples include JSON and XML.

[1179] "Grant Information" refers to information regarding financial assistance provided by government or private sources.

[1180] "Competitor trends" refers to the current activities and market movements of competing companies.

[1181] "Data collection method" refers to the technology or method used by the server to obtain the required information, such as an API call or web scraping.

[1182] "Data analysis tools" refers to techniques and methods for processing collected data and extracting meaningful information. Examples include natural language processing and machine learning.

[1183] "Proposal Ideas" refers to specific plans and strategies for increasing profitability and efficiency of business entities, which are generated based on collected and analyzed data.

[1184] "List display means" refers to a technique or method for visually displaying the generated proposed ideas.

[1185] "Advanced search conditions" refers to search criteria used to narrow down proposed ideas to those that meet specific conditions.

[1186] "Detailed analysis means" refers to techniques and methods for conducting deeper analysis based on detailed search conditions.

[1187] "Specific period" refers to the time or period required to implement the proposed idea.

[1188] "Estimated amount" refers to the budget and expenses required to implement the proposed idea.

[1189] "Profit potential" refers to an indicator that shows how much revenue a proposed idea has the potential to generate.

[1190] "Generative AI model" refers to artificial intelligence techniques or machine learning models used to analyze data and generate meaningful information or recommendations.

[1191] A "prompt sentence" refers to an instruction or inquiry sentence to be input into a generative AI model.

[1192] This invention is a system that efficiently collects and analyzes the information necessary for businesses and organizations (hereinafter referred to as "business entities") to receive support, and generates proposals. This system allows businesses to easily find optimal grant and market opportunities and develop strategies to increase revenue.

[1193] Hardware and software used

[1194] Terminal: A device used by a user to enter the name of the business, type of business, and other necessary information. Examples include a personal computer or smartphone.

[1195] Server: The central processing unit that collects data, analyzes it, and generates recommendations. It can be a cloud-based server or a dedicated server.

[1196] Software: Natural language processing (NLP) libraries (e.g., SpaCy, NLTK), machine learning frameworks (e.g., scikit-learn, TensorFlow), scraping tools for data collection (e.g., BeautifulSoup, Scrapy), libraries for API connectivity (e.g., Requests).

[1197] Program processing flow

[1198] First, the user uses a terminal to input the business entity name (e.g., "Y Corporation"), business type (e.g., "manufacturing"), and other necessary information (e.g., "new product development"). The terminal collects this information and converts it into a standard data format such as JSON. Specifically, it uses JavaScript or Python functions to convert the data into JSON format.

[1199] The terminal then sends the converted data to the server using an HTTP POST request. The server receives the data and stores it in a database. The server then collects the necessary information from government grant information APIs, news websites, and industry databases. The API requests are sent using Python's Requests library, and the resulting data is received in JSON format. Web scraping can also be performed using BeautifulSoup or Scrapy.

[1200] The collected data is analyzed on a server. At this time, natural language processing technology (SpaCy, NLTK) and machine learning technology (scikit-learn, TensorFlow) are used to generate proposed ideas based on the information entered by the user. For example, if a business is in the manufacturing industry, proposals such as "utilizing digitalization promotion subsidies" or "utilizing new product development support programs" may be generated.

[1201] The server compiles the generated proposal ideas into a list and sends it to the terminal as an HTTP response. The terminal receives this and displays it on the screen in an easy-to-read format for the user. The user selects the proposals that interest them from the list and sets detailed search conditions (e.g., region "Tokyo" and upper budget limit "10 million yen"). The settings are sent back to the server, which performs further detailed analysis.

[1202] The server completes the detailed analysis and generates results including specific timeframes, estimated amounts, and profit potential, which are sent in JSON format to the terminal, which then displays them visually to the user.

[1203] Specific examples

[1204] For example, consider a case where a user is searching for a proposal idea that is likely to generate revenue for a manufacturing business entity, "Y Co., Ltd." The user enters the business entity name, "Y Co., Ltd.", the business type, "manufacturing," and "new product development" into a terminal. The terminal converts this data into JSON format and sends it to the server via an HTTP POST request. The server receives this and collects the latest information from grant information APIs and news websites. The server then uses natural language processing and machine learning techniques to generate proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services for new products."

[1205] The generated proposal ideas are sent in list form to the device, which displays them to the user. When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 10 million yen," the device resends this to the server, which performs a detailed analysis. Finally, the user is provided with information such as the specific project period, required budget, and projected profitability.

[1206] Prompt Sentence Examples

[1207] Enter the following prompt into the generative AI model:

[1208] "The business name is 'Y Co., Ltd.', the business type is 'manufacturing', and the required information is 'new product development'. Please collect the latest subsidy information and competitor trends, and generate proposal ideas that are expected to generate profits based on that information. Display the generated idea list and allow the user to set detailed conditions."

[1209] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1210] Step 1:

[1211] The user uses the device to enter the business entity name, type of business, and other necessary information. Specifically, the user operates the keyboard or touch panel to enter information such as "Y Co., Ltd.", "manufacturing industry," and "new product development." The entered data is converted to JSON format within the device. For example, the data can be converted to JSON format using the JavaScript JSON.stringify() function.

[1212] Input: Name of business entity, type of business, other necessary information

[1213] Output: Input data in JSON format

[1214] Step 2:

[1215] The terminal sends the converted JSON data to the server. Specifically, the data is sent using an HTTP POST request. The data sent from the terminal is received by the server. The received data is stored in a database.

[1216] Input: Input data in JSON format

[1217] Output: Send data to the server, store data in the database on the server

[1218] Step 3:

[1219] The server uses the collected database to gather information on grants and competitor trends, specifically by using API connections and web scraping. For example, it uses the Requests and BeautifulSoup libraries to gather information from government grant information APIs and industry news sites.

[1220] Input: Data stored in the database on the server

[1221] Output: Subsidy information and competitor trends data

[1222] Step 4:

[1223] The server analyzes the collected data and generates proposal ideas. Specifically, it analyzes the data using natural language processing (NLP) and machine learning models (generative AI models). For example, it uses Scikit-learn and TensorFlow to generate proposals that are beneficial to the business. It creates specific proposal ideas such as "utilizing digitalization promotion subsidies" and "utilizing new product development support programs."

[1224] Input: Grant information and competitor trends data

[1225] Output: Proposed Idea

[1226] Step 5:

[1227] The server compiles the generated proposal ideas into a list and converts it into JSON format. It then sends this to the device using an HTTP response. The device then visually displays the received data to the user using HTML and JavaScript. For example, it displays a list so that the user can easily click to see the details.

[1228] Input: Proposed idea

[1229] Output: A list of proposed ideas sent to the device

[1230] Step 6:

[1231] The user selects ideas that interest them from the suggestions and sets detailed search criteria. For example, they can use drop-down menus and radio buttons to set "Region: Tokyo" and "Budget limit: 10 million yen." The search criteria are then converted back to JSON format and sent to the server using an HTTP POST request.

[1232] Input: Selected proposal idea and detailed search criteria

[1233] Output: Detailed search criteria data in JSON format

[1234] Step 7:

[1235] The server then performs further analysis based on the received search criteria data, such as determining the availability of grants, budget estimates, and profitability forecasts for the selected proposals, by making additional database queries or API requests.

[1236] Input: Detailed search criteria data

[1237] Output: Detailed analysis result data

[1238] Step 8:

[1239] The server converts the detailed analysis results data into JSON format and sends it to the terminal as an HTTP response. The terminal then visually displays the received data to the user using HTML and JavaScript. Specifically, it uses tables and graphs to display detailed results such as specific periods, estimated amounts, and predicted profitability.

[1240] Input: Detailed analysis result data

[1241] Output: Detailed results displayed on the terminal

[1242] (Application example 1)

[1243] 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."

[1244] In conventional logistics centers, data collection on subsidy information and competitor trends is rare, resulting in the problem that formulating an efficient operation strategy takes time and effort. Furthermore, data analysis is insufficient, making it difficult to generate profitable proposal ideas.

[1245] 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.

[1246] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for displaying specific periods, estimated amounts, and profitability, and means for collecting operational data of the logistics center and proposing strategies for improving efficiency. This makes it possible to formulate an efficient and profitable operational strategy for the logistics center.

[1247] A "business name" is a name used to identify a particular company or organization.

[1248] "Industry" is a category that indicates the classification of a particular industry or business activity.

[1249] A "requirement" is an item of information or data that is essential for the operation of a system or process.

[1250] A "data format" is a format that organizes and structures information in a particular way.

[1251] "Funding Information" means information about funding support or grants provided by governments or other agencies.

[1252] "Competitor activity" is information about the recent activities and strategies of other companies or organizations competing in the same industry.

[1253] "Collection" is the act of gathering necessary data and information.

[1254] "Analysis" is the process of analyzing collected data and information in detail to derive meaning and patterns.

[1255] A "proposal idea" is a concept of a specific plan or strategy for achieving a specific goal.

[1256] "List display" refers to the act of presenting the generated proposed ideas and information to the user in list form.

[1257] "Detailed search conditions" are conditions for obtaining more specific information based on the user's needs.

[1258] "Detailed analysis" is the process of conducting a deeper level of data analysis based on the results of the initial analysis.

[1259] A "period" is a time frame that indicates the duration of a particular activity or project.

[1260] "Estimate" means the projected cost required to carry out a particular project or activity.

[1261] "Profitability" is a measure of how much profit a particular activity or project generates.

[1262] A "logistics center" is a base for storing, distributing, and managing goods.

[1263] "Operational data" refers to information and statistics about the operating status of a particular system or process.

[1264] An efficiency improvement strategy is a plan to improve and optimize the performance of existing processes and systems.

[1265] "Natural language processing" is a technology that allows computers to understand, interpret, and generate human language.

[1266] "Machine learning" is a branch of artificial intelligence in which algorithms improve themselves based on data.

[1267] A "generative AI model" is an artificial intelligence model that can generate new content and predictions based on data.

[1268] A "prompt" is text that is input to a generative AI model and serves to guide the output that the model generates.

[1269] This invention is a system for proposing strategies to improve efficiency in a logistics center. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1270] First, the user uses a terminal to input the company name, industry, and other necessary information. For example, they provide information such as "Company A," "Logistics industry," and "Improvement of transportation efficiency." This information is converted into a data format (e.g., JSON format).

[1271] The converted data is sent from the device to a server, which collects the latest grant information and competitor trends from multiple sources (subsidy information APIs, industry news sites, databases, etc.) using APIs and web scraping technology.

[1272] The collected data is analyzed using natural language processing (NLP) and machine learning (ML) techniques. During the analysis, a generative AI model is used to generate profitable proposal ideas based on user input. For example, it may suggest "optimizing transportation routes" or "introducing a new delivery system."

[1273] The generated proposal ideas are compiled into a list and sent to the device. The user can review this and select the proposal ideas they are interested in. By setting detailed search conditions (e.g., region restrictions, budget limits), the device will again send the conditions to the server.

[1274] The server then performs a more detailed analysis based on the search criteria. Specifically, it calculates the availability of grant funds, budget estimates, and profitability forecasts for the selected proposal ideas. The results of the detailed analysis are sent to the device, where specific information such as the time frame, estimated amount, and profitability are displayed.

[1275] For example, if a user selects "Transportation Route Optimization" for "Company A" and sets the detailed conditions as "Region: Tokyo" and "Budget Limit: 5 million yen," the server will perform a detailed analysis based on this and provide information such as the specific duration of the initiative, the required budget, and projected profitability.

[1276] An example of a prompt is:

[1277] "A company that operates Logistics Center A is aiming to improve transportation efficiency. Based on information about subsidies and the situation of competitors, please generate profitable proposal ideas and present a specific implementation period and estimated costs."

[1278] This system will enable logistics centers to develop efficient and profitable operational strategies.

[1279] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1280] Step 1:

[1281] The user uses the terminal to input the business name, industry, and other necessary information. For example, they provide information such as "Company A," "logistics industry," and "improved transport efficiency." The terminal then converts this information into JSON format. The input includes the data entered by the user, such as "Company A," "logistics industry," and "improved transport efficiency," and the output is the data converted into JSON format.

[1282] Step 2:

[1283] The terminal sends the converted JSON-formatted data to the server. The server saves the received data in preparation for analysis. Specifically, the terminal sends the JSON data as an HTTP POST request, and the server saves the received data in a database. The input is the JSON data sent from the terminal, and the output is in the format saved in the database on the server.

[1284] Step 3:

[1285] The server collects data on grant information and competitor trends from multiple sources (e.g., grant information APIs, industry news sites, and databases). This collection is done using API requests and web scraping techniques. For example, grant information is obtained by sending an API request, and competitor trends are collected by web scraping. The input is the API request or scraping URL from the server, and the output is the obtained grant information and competitor trend data.

[1286] Step 4:

[1287] The server analyzes the collected data using natural language processing (NLP) and machine learning (ML) techniques and generates proposed ideas using a generative AI model. For example, it analyzes grant information and industry news to generate efficiency improvement strategies tailored to the user's needs. The input is the collected grant information and competitor trends data, and the output is a list of generated proposed ideas.

[1288] Step 5:

[1289] The generated proposed ideas are compiled into a list and sent to the device. The device displays the received data on the screen. Specifically, the server sends the proposed idea list to the device in JSON format, which the device parses and displays in a format that is easy for the user to check. The input is the proposed idea list data sent from the server, and the output is the data displayed on the screen.

[1290] Step 6:

[1291] The user selects the proposal ideas that interest them using their device and sets detailed search conditions (e.g., region restriction, budget limit). For example, they enter conditions such as "region: Tokyo" and "budget limit: 5 million yen." The input is the detailed search conditions set by the user, and the output is data converted from those conditions into JSON format.

[1292] Step 7:

[1293] The device sends the set search criteria to the server, which then performs more detailed analysis based on the received criteria. For example, it may determine the availability of subsidies, estimate the budget, or predict profitability. The input is the data for the detailed search criteria sent from the device, and the output is the data of the analysis results.

[1294] Step 8:

[1295] The server generates the results of the detailed analysis and sends them to the terminal. The terminal displays the received data on the screen so that the user can check it. For example, it displays a list of specific time periods, estimated amounts, and profitability information. The input is the data of the detailed analysis results sent from the server, and the output is the specific time period, estimated amounts, and profitability information displayed on the screen.

[1296] 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.

[1297] The present invention provides a system including a means for inputting the name of a business, type of business, and other necessary information, a means for converting the input information into a data format and transmitting it, a means for collecting data on subsidy information and competitor trends, a means for analyzing the collected data and generating proposal ideas, a means for displaying a list of the generated proposal ideas, a means for setting detailed search conditions for the proposal ideas, a means for performing a more detailed analysis based on the set search conditions, and a means for displaying a specific period, estimated amount, and profitability.In addition, by combining this with an emotion engine that recognizes the user's emotions, the system achieves an even more advanced user experience.

[1298] Step 1: User Input and Initial Settings

[1299] The user uses the terminal to input the business name, industry, and other necessary information. For example, they might provide information such as "X Corporation," "manufacturing," and "new product development." The terminal collects this information and converts it into a data format (e.g., JSON format).

[1300] Step 2: Submit your input

[1301] The terminal sends the converted data format information to the server, where a validation check is performed to ensure the data is complete and consistent.

[1302] Step 3: Gathering grant information and competitor trends

[1303] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[1304] Step 4: Analyze user emotions with the emotion engine

[1305] The emotion engine analyzes facial expressions and voice data while the user is typing or operating the device, and recognizes the user's emotional state in real time. This emotional data is also sent to the server and used for analysis.

[1306] Step 5: Analyze the data and generate proposal ideas

[1307] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it considers ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[1308] Step 6: Listing the proposed ideas

[1309] The generated proposal ideas are compiled into a list and sent to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[1310] Step 7: Setting advanced search criteria

[1311] Users select ideas that interest them and set detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[1312] Step 8: Detailed analysis

[1313] The server then performs a more detailed analysis based on the search criteria set by the user, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts.

[1314] Step 9: View detailed results

[1315] The server generates detailed analysis results and sends specific information on the period, estimated amount, and profitability to the terminal, which receives the results and displays them on the screen for the user to review.

[1316] Specific examples

[1317] For example, consider the case where a user is searching for a profitable proposal idea for a manufacturing company, "X Corporation." When the user enters the company name, "X Corporation," the industry, "manufacturing," and "new product development," the server receives this information and collects the latest subsidy information and competitor trends. Furthermore, the emotion engine analyzes the user's emotions from their facial expressions and voice while they are entering information, and their emotional state is also sent as data to the server.

[1318] The server analyzes this data and generates proposal ideas such as "Utilizing the Digitalization Promotion Subsidy" and "Deploying a new product as a cloud service." When the user selects "Utilizing the Digitalization Promotion Subsidy" and sets detailed conditions such as "Region: Tokyo" and "Budget Limit: 10 million yen," the server performs a detailed analysis based on this and provides information such as the specific implementation period, required budget, and projected profitability. The user's emotional state is also continuously monitored, allowing for interactive responses tailored to the displayed results.

[1319] The processing flow will be explained below.

[1320] Step 1:

[1321] The user uses the terminal to input the company name, industry, and other necessary information. For example, the user inputs information such as "X Corporation," "manufacturing industry," and "new product development."

[1322] Step 2:

[1323] The device converts the input information into JSON format and sends it to the server, where it performs validation checks to ensure data integrity and consistency.

[1324] Step 3:

[1325] The device sends the user's facial expressions and voice to the emotion engine in real time to collect the user's emotional data. The emotion engine analyzes the emotional data and identifies the user's emotional state. This emotional data is also converted into JSON format and sent to the server.

[1326] Step 4:

[1327] The server receives the JSON data (input information and emotion data) sent from the device and prepares it for analysis.

[1328] Step 5:

[1329] The server collects data on the latest grant information and competitor trends from multiple sources (e.g., government grant APIs, industry news sites, and other databases) using API calls and web scraping.

[1330] Step 6:

[1331] The server analyzes the collected data and emotional data. Using natural language processing (NLP) and machine learning (ML) algorithms, it generates profitable proposal ideas based on the user's input and emotional state. For example, it could suggest ideas such as "utilizing digitalization promotion subsidies" or "developing cloud services for new products."

[1332] Step 7:

[1333] The server generates a list of proposed ideas and sends it to the device, which receives it and displays it on the screen in a format that is easy for the user to check.

[1334] Step 8:

[1335] The user selects the ideas they are interested in from the suggestions and sets detailed search criteria (e.g., region restrictions, budget limit). At this point, the emotion engine analyzes the user's emotional changes and suggests or adjusts search criteria as necessary.

[1336] Step 9:

[1337] The terminal converts the detailed search conditions set by the user into JSON format and sends it to the server.

[1338] Step 10:

[1339] The server receives the detailed search conditions and emotion data and performs further detailed analysis, including determining whether or not to use subsidies based on the newly set conditions, estimating budgets, and forecasting revenue.

[1340] Step 11:

[1341] The server generates the results of the detailed analysis in JSON format and sends them to the terminal.

[1342] Step 12:

[1343] The device analyzes the detailed results received from the server and visually displays them for the user to review. The display includes specific timeframes, estimated amounts, and profitability information. The emotion engine continuously monitors the user's emotions and provides interactive responses tailored to the displayed results.

[1344] Step 13:

[1345] The user reviews the detailed results presented and makes a final decision. The emotion engine analyzes the user's emotional state and provides appropriate advice and guidance when support is required.

[1346] Example 2

[1347] 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."

[1348] In today's business environment, companies need to quickly and accurately grasp a wide range of information, such as subsidy information and competitor trends. They also need to generate specific proposal ideas and create detailed, actionable plans based on this information. However, existing systems often take time to collect and analyze large amounts of data and are unable to provide interactive responses that take into account the user's emotional state. This makes it difficult for companies to receive the appropriate support at the right time.

[1349] 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.

[1350] In this invention, the server includes means for inputting the business name, industry, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposal ideas, means for displaying a list of the generated proposal ideas, means for setting detailed search conditions for the proposal ideas, means for performing a more detailed analysis based on the set search conditions, means for analyzing the user's emotions using an emotion recognition engine and transmitting the emotion data to the server, and means for displaying the specific period, estimated amount, and profitability. This allows users to quickly and accurately obtain proposal ideas, and further enables interactive and individual responses through real-time emotion analysis.

[1351] "Business name" refers to the name of a company or organization.

[1352] "Industry" refers to the type or category of business conducted by a company or organization.

[1353] "Requirements" refers to items of information that a user must enter in order for the system to function properly.

[1354] "Input information" refers to the collection of data that a user provides to a system.

[1355] "Data format" refers to a particular format for structuring information.

[1356] "Subsidy information" refers to information about various subsidies that companies and organizations can apply for.

[1357] "Competitors" refers to other companies or organizations in the same market or industry that offer similar products or services.

[1358] "Trends" refers to current trends and changes in a market or industry.

[1359] "Means of collecting data" refers to the mechanisms and tools used to obtain the necessary information.

[1360] "Means of analysis" refers to the mechanisms and methods for analyzing and processing collected data.

[1361] "Proposed Ideas" refers to specific action plans that are generated based on the collected and analyzed information.

[1362] The "means for displaying a list" refers to a method for visually presenting the generated proposed ideas to the user.

[1363] "Advanced search conditions" refer to conditions set by the user to further narrow down the proposed ideas.

[1364] An "emotion recognition engine" refers to technology for analyzing a user's emotional state in real time.

[1365] The "specific period" refers to the period during which the action to be taken is to be carried out.

[1366] "Estimated Amount" refers to an estimate of the costs required to implement the proposed idea.

[1367] "Profitability" refers to an indicator that evaluates the economic benefits that a proposed idea brings.

[1368] "Natural language processing" refers to the technology that enables computers to understand, interpret, and generate human language.

[1369] "Machine learning" refers to a technology that analyzes data, automatically learns, and makes predictions and judgments.

[1370] A "structured data format" refers to a data format that is organized based on specific rules.

[1371] The present invention provides a system that enables companies and businesses to quickly provide optimal subsidy information and specific proposal ideas, and also enables interactive responses that take into account the emotional state of the user. Specific embodiments of the system are described below.

[1372] First, the user uses the terminal to enter the company name, industry, and other necessary information. For example, if the entered information is "X Corporation," "manufacturing," and "new product development," the terminal collects this information and converts it into a data format such as JSON. The terminal then sends the converted data to the server. At this time, the terminal performs a validation check to ensure the data is complete and consistent.

[1373] Based on the received data, the server collects data on the latest grant information and competitor trends from multiple sources, specifically using API calls and web scraping techniques to obtain information from government grant APIs, industry news sites, etc. The collected data is then stored in an internal database.

[1374] Furthermore, an emotion recognition engine is used to analyze the user's emotions. While the user is typing or operating the device, facial expressions and voice data are captured using a webcam and microphone, and an analysis algorithm is used to recognize the user's emotional state. This emotional data is sent to the server and used for subsequent analysis.

[1375] The server analyzes the collected data and emotional data. Specifically, it applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's input and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" are considered.

[1376] The generated proposal ideas are sent from the server to the device, which displays them in list form to the user. The user selects the proposal ideas that interest them from the displayed list and sets detailed search conditions (e.g., "Area limited: Tokyo," "Budget limit: 10 million yen"). The emotion recognition engine analyzes changes in the user's emotions and suggests or adjusts search conditions as necessary.

[1377] The server then performs a more detailed analysis based on the search criteria that was set, including determining whether or not to use subsidies based on the newly set criteria, budget estimates, and revenue forecasts. The detailed analysis results generated by the server are sent to the terminal, and specific information on the period, estimated amount, and profitability is presented to the user.

[1378] For example, when a user enters "X Corporation," "manufacturing," and "new product development," the device converts this into JSON format, resulting in something like "{ 'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The device then sends this data to the server, which uses government_grants_api and industry_news_scraper to collect information on grants and competitor trends. The acquired data is analyzed, and proposal ideas such as "utilizing digitalization promotion grants" and "developing cloud services" are generated.

[1379] (Example of a specific prompt sentence)

[1380] "Please tell me about digitalization subsidies related to new product development in the manufacturing industry. The specific conditions are that they are limited to Tokyo and have a budget cap of 10 million yen."

[1381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1382] Step 1:

[1383] The user uses the terminal to enter the company name, industry, and other necessary information. For example, they might enter information such as "X Corporation, manufacturing, new product development." The terminal receives this input information and converts it into a data format such as JSON. Specific input data is text information such as "X Corporation" and "manufacturing," which is converted into structured data such as "{'Company Name': 'X Corporation', 'Industry': 'Manufacturing', 'Project': 'New Product Development'}." The converted data is then ready to be sent to the server.

[1384] Step 2:

[1385] The terminal sends the information in the converted data format to the server. At this time, the terminal performs a validation check to maintain the completeness and consistency of the data. Specifically, it checks whether the input data is missing or is in the correct format. For example, it checks whether the company name "X Co., Ltd." is in the correct format and whether the industry is within the options. Once the check is complete, the data is sent to the server via an HTTP request. The server checks the contents of the received data and proceeds with the next process.

[1386] Step 3:

[1387] The server collects data on grant information and competitor trends from multiple sources. Specifically, it calls government grant APIs and web scrapes industry news sites. This process involves sending requests to API endpoints to obtain grant information in JSON format. It also uses web scraping tools to obtain competitor news articles and analytical reports. The collected data is stored in the server's internal database. This allows it to accumulate the latest grant information and competitor trends.

[1388] Step 4:

[1389] An emotion recognition engine analyzes facial and voice data while the user is typing or operating the device to recognize the user's emotional state. For example, a webcam or microphone can be used to capture the user's facial expressions and tone of voice. This data is analyzed in real time to identify the user's emotional state (e.g., joy, surprise, distress, etc.). This emotional data is also sent to the server and used as material for analysis along with other data.

[1390] Step 5:

[1391] The server performs analysis using the collected data and emotional data. It then applies natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas based on the user's needs and emotional state. For example, proposals such as "utilizing digitalization promotion subsidies" and "developing cloud services for new products" may be generated. The server then compiles these proposal ideas into a list and records the selection process. This allows the server to verify that the generated proposal ideas are based on concrete evidence.

[1392] Step 6:

[1393] The generated proposal ideas are sent to the device. The device receives them and displays them on the screen in list format so that the user can easily check them. For example, each proposal idea can be presented in an easy-to-understand card format, with links and buttons for the user to view the details. This list-format proposal display allows the user to compare and select at a glance.

[1394] Step 7:

[1395] Users select proposal ideas that interest them from a list and set detailed search criteria. For example, they can enter regional restrictions (e.g., "Tokyo") or budget limits (e.g., "10 million yen"). While they are entering their search criteria, the emotion recognition engine analyzes the user's emotional changes and makes appropriate suggestions or adjustments. The input data based on the detailed search criteria is sent to the server, where further detailed analysis begins.

[1396] Step 8:

[1397] The server performs further detailed analysis based on the set search criteria. Based on the newly set criteria, it determines whether grants are available, estimates budgets, and forecasts revenue. It uses data analysis tools to generate detailed reports, such as "subsidies available based on local conditions," recommended "budget plans," and "projected profitability." The analysis results are prepared for the next step.

[1398] Step 9:

[1399] The server generates detailed analysis results and sends them to the terminal, which then displays specific information on the duration, estimated cost, and profitability. The terminal then receives this information and displays it on the screen in a format that is easy for the user to understand. For example, presenting information using visual elements, such as a Gantt chart showing the project duration or a bar chart showing a comparison of costs and profitability, helps users understand the information better.

[1400] In this way, the system can effectively carry out a series of processes from user input to providing detailed analysis results.

[1401] (Application example 2)

[1402] 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."

[1403] This invention aims to improve productivity in factories by analyzing the latest subsidy information and competitor trends to generate and display specific and profitable proposal ideas, thereby solving the problem of realizing an efficient manufacturing process. It is also required to increase user satisfaction and interest by taking into account the user's emotional state.

[1404] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting the name of the business, type of business, and other necessary information, means for converting the input information into a data format and transmitting it, means for collecting data on subsidy information and competitor trends, means for analyzing the collected data and generating proposed ideas, means for analyzing the user's emotional state using an emotion recognition engine and transmitting the data, means for displaying a list of the generated proposed ideas, means for setting detailed search conditions for the proposed ideas, means for performing further detailed analysis based on the set search conditions, and means for displaying specific periods, estimated amounts, and profitability. This makes it possible to generate and display profitable proposed ideas that take the user's emotions into consideration.

[1405] "Business name" is the name of a corporation or sole proprietorship.

[1406] "Industry" refers to the type of industry to which a business operator belongs.

[1407] "Required information" refers to information required to identify businesses and generate proposal ideas.

[1408] "Input information" refers to the business name, industry, and other necessary information that the user provides to the system.

[1409] A "data format" is input information converted into a form that is easy for a program to process.

[1410] "Grant Information" refers to detailed data about grants.

[1411] "Competitor Trends" is data that shows the activities and strategies of competitors in the market.

[1412] "Means of collecting data" refers to methods and technologies for obtaining subsidy information and competitor trends.

[1413] "Means for analyzing data" refers to the technology that processes collected data to generate useful proposal ideas.

[1414] "Proposed ideas" are specific initiatives that will increase profitability and efficiency for users.

[1415] An "emotion recognition engine" is a technology that analyzes a user's emotional state from their facial expressions and voice.

[1416] "Emotion data" is information about the user's emotional state obtained by an emotion recognition engine.

[1417] The "means for displaying proposed ideas" is a technique for visually presenting the generated proposed ideas in a format that can be confirmed by the user.

[1418] The "detailed search conditions" indicate the user's specific requirements and constraints for the proposed idea.

[1419] The "means for performing detailed analysis based on search conditions" is a technique for performing more specific data analysis based on detailed search conditions set by the user.

[1420] The "specific period" refers to the time required to implement the proposed idea.

[1421] The "estimated amount" is the budget amount required to implement the proposed idea.

[1422] "Profitability" refers to the revenue expected from implementing the proposed idea.

[1423] In this invention, the system operates in the following steps.

[1424] First, the user uses a tablet device to enter the business name, industry, and other necessary information. Specifically, they enter the company name, industry type (e.g., manufacturing), and specific project name (e.g., new product development). This information is converted into a data format and sent to the server in a standard format such as JSON. This ensures data consistency and integrity.

[1425] The server then uses multiple sources to gather data on grant information and competitor activity, including government APIs, industry news sites, and other trusted databases to obtain the latest information, using techniques such as API calls and web scraping.

[1426] The emotion recognition engine then analyzes the user's emotional state. The engine analyzes the user's facial expressions and voice data as they are inputting, recognizing their emotional state in real time. This emotional data is also sent to the server and used for analysis in the next step.

[1427] The collected data and sentiment data are analyzed using natural language processing (NLP) and machine learning (ML) algorithms. This generates profitable proposal ideas. For example, specific proposals such as utilizing digitalization promotion subsidies or developing cloud services for new products are considered. The generated proposal ideas are compiled into a list and sent to the device, where they are displayed to the user.

[1428] Users can set detailed search conditions for proposed ideas, such as region restrictions or budget limits. Based on the set search conditions, the server performs further detailed analysis. The detailed analysis includes determining whether or not subsidies can be used based on the newly set conditions, budget estimates, revenue forecasts, etc.

[1429] Finally, the server sends the results of the detailed analysis to the terminal, and the specific time frame, estimated cost, and profitability information are displayed to the user, providing them with specific and actionable suggestions for improving profitability and efficiency.

[1430] Hardware and Software Used

[1431] The hardware used mainly includes tablets and factory robots, while the software uses an emotion recognition engine (EmotionEngine), natural language processing and machine learning libraries (NLP and ML), and a REST API.

[1432] Specific examples

[1433] For example, a factory worker is searching for information on subsidies for a new product. When the worker uses a tablet to enter the necessary information, an emotion recognition engine analyzes the worker's emotional state, such as interest and stress level, from his facial expressions and voice. The server analyzes the collected subsidy information and competitive information and generates specific proposals such as "utilizing digitalization promotion subsidies." When the worker sets more detailed conditions for this proposal, the server performs detailed analysis, such as budget estimates and revenue forecasts, and displays the results.

[1434] Prompt Sentence Examples

[1435] You are an assistant tasked with generating proposal ideas that will contribute to improving factory productivity based on the information below. Please come up with ideas based on the information below.

[1436] Factory Information:

[1437] Business name: Y Co., Ltd.

[1438] Industry: Manufacturing

[1439] Process: New Product Development

[1440] Grant information: [JSON data of grant information]

[1441] Competitor Information: [JSON data of competitor information]

[1442] Worker emotional state: [JSON data of emotion data]

[1443] request:

[1444] Generate three proposal ideas.

[1445] For each proposal, explain the projected profitability.

[1446] View the list of suggestions.

[1447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1448] Step 1:

[1449] The user uses a tablet device to enter the business name, industry, and other necessary information. This allows for the collection of corporate names, industry types, and specific project names such as new product development. The entered information is converted into a data format such as JSON and sent to the server. Input is done in text or multiple choice format, and the information converted into data format is output.

[1450] Step 2:

[1451] The server receives the submitted data and validates it for consistency and completeness. Data that passes the validation checks is used to collect data on grant information and competitor trends. The input is transformed JSON data and the output is a valid dataset.

[1452] Step 3:

[1453] The server uses government APIs, industry news sites, and other reliable databases to collect the latest grant information. It also collects competitors' technology and productivity improvement trends. This information is collected using API calls and web scraping. The input is the API key and web scraping settings, and the output is the latest grant information and competitor trends.

[1454] Step 4:

[1455] While the user is inputting, the emotion recognition engine analyzes the user's facial expression and voice data to recognize their emotional state in real time. This emotion data is also sent to the server and used for analysis in the next step. The input is the user's facial expression and voice data, and the output is the analyzed emotion data.

[1456] Step 5:

[1457] The server analyzes the collected grant information, competitive information, and user sentiment data. It uses natural language processing (NLP) and machine learning (ML) algorithms to generate profitable proposal ideas. Specific proposal ideas considered include "utilizing digitalization promotion subsidies" and "developing cloud services for new products." The input is the collected dataset and sentiment data, and the output is the generated proposal ideas.

[1458] Step 6:

[1459] The generated proposal ideas are compiled in list form and sent to the terminal. The user can check this and view the details of each proposal idea. The input is the generated proposal ideas, and the output is the proposal ideas compiled in list form.

[1460] Step 7:

[1461] Users input detailed search criteria for their proposed ideas, such as geographical restrictions or budget limits. The system uses an emotion recognition engine to suggest and adjust search criteria as needed. The input is the detailed search criteria set by the user, and the output is a dataset that reflects the detailed search criteria.

[1462] Step 8:

[1463] The server performs further detailed analysis based on the set detailed search conditions. Based on the newly set conditions, it determines whether or not subsidies can be used, estimates budgets, and predicts revenue. The input is the detailed search conditions, and the output is the results of the detailed analysis.

[1464] Step 9:

[1465] The server generates the results of the detailed analysis and sends them to the terminal. The user can then check the specific period, estimated amount, and profitability information. The input is the detailed analysis results, and the output is the specific period, estimated amount, and profitability information.

[1466] Through these processing steps, users can obtain specific and actionable suggestions for increasing profitability and efficiency.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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).

[1474] 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.

[1475] 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."

[1476] 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.

[1477] 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).

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] The following is further disclosed regarding the above embodiment.

[1489] (Claim 1)

[1490] A means of entering the business name, industry, and other necessary information;

[1491] means for converting input information into a data format and transmitting the data;

[1492] a means of collecting data on grant information and competitor activity;

[1493] A means of analyzing the collected data and generating proposal ideas;

[1494] A means for displaying a list of generated proposal ideas;

[1495] a means for setting detailed search criteria for the proposed ideas...

Claims

1. A means of entering the business name, industry, and other necessary information; means for converting input information into a data format and transmitting the data; a means of collecting data on grant information and competitor activity; A means of analyzing the collected data and generating proposal ideas; A means for displaying a list of generated proposal ideas; a means for setting detailed search criteria for the proposed ideas; A means for performing further detailed analysis based on the search criteria set; A means to display specific timeframes, estimated amounts, and profitability; A system including:

2. The system of claim 1 , wherein the collected data is analyzed using natural language processing and machine learning.

3. The system according to claim 1, wherein detailed information based on the proposed idea is sent and received in JSON format.

Images